Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.9263. Min Act: -0.1700
Data Index: 6031085 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.8325. Min Act: -0.1700
Data Index: 7170331 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.8013. Min Act: -0.1700
Data Index: 6235882 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.8013. Min Act: -0.1700
Data Index: 1876223 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.8013. Min Act: -0.1700
Data Index: 2635315 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.7700. Min Act: -0.1700
Data Index: 8546485 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.7075. Min Act: -0.1700
Data Index: 1429653 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.7075. Min Act: -0.1700
Data Index: 6019185 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.6138. Min Act: -0.1700
Data Index: 3328613 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.5825. Min Act: -0.1700
Data Index: 4844954 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.5825. Min Act: -0.1700
Data Index: 4817338 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.5825. Min Act: -0.1700
Data Index: 8071252 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.5513. Min Act: -0.1700
Data Index: 6883989 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.5200. Min Act: -0.1700
Data Index: 2651746 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.5200. Min Act: -0.1700
Data Index: 3934472 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.4888. Min Act: -0.1700
Data Index: 4379025 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.4888. Min Act: -0.1700
Data Index: 8715459 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.4888. Min Act: -0.1700
Data Index: 7885472 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.4888. Min Act: -0.1700
Data Index: 6409725 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9263. Min Range: -5.9263
Max Act: 5.4575. Min Act: -0.1700
Data Index: 2551008 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19