Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.8042. Min Range: -12.8042
Max Act: 12.8042. Min Act: -0.1700
Data Index: 1077315 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8042. Min Range: -12.8042
Max Act: 12.6167. Min Act: -0.1700
Data Index: 1427822 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8042. Min Range: -12.8042
Max Act: 12.3042. Min Act: -0.1700
Data Index: 1077324 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.9917. Min Act: -0.1700
Data Index: 1243841 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.9917. Min Act: -0.1700
Data Index: 1543782 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.8667. Min Act: -0.1700
Data Index: 8252402 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.9292. Min Act: -0.1699
Data Index: 338266 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.8042. Min Act: -0.1700
Data Index: 5462135 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.7417. Min Act: -0.1700
Data Index: 6446526 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.5542. Min Act: -0.1700
Data Index: 2815018 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.5542. Min Act: -0.1700
Data Index: 4322037 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.4917. Min Act: -0.1700
Data Index: 8639710 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.4292. Min Act: -0.1700
Data Index: 258371 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.4917. Min Act: -0.1700
Data Index: 7328011 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.4292. Min Act: -0.1700
Data Index: 5464387 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.3667. Min Act: -0.1700
Data Index: 8617772 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.3042. Min Act: -0.1700
Data Index: 1710540 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.3042. Min Act: -0.1700
Data Index: 123913 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.4292. Min Act: -0.1699
Data Index: 8633362 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8042. Min Range: -12.8042
Max Act: 11.2417. Min Act: -0.1700
Data Index: 4224627 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19