Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4542. Min Range: -6.4542
Max Act: 6.4542. Min Act: -0.1700
Data Index: 3802635 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4542. Min Range: -6.4542
Max Act: 6.2042. Min Act: -0.1700
Data Index: 4036019 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4542. Min Range: -6.4542
Max Act: 6.2042. Min Act: -0.1700
Data Index: 1364806 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4542. Min Range: -6.4542
Max Act: 6.1417. Min Act: -0.1700
Data Index: 2768256 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4542. Min Range: -6.4542
Max Act: 6.0480. Min Act: -0.1700
Data Index: 7721917 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4542. Min Range: -6.4542
Max Act: 6.0480. Min Act: -0.1700
Data Index: 537988 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.9230. Min Act: -0.1700
Data Index: 2179633 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8917. Min Act: -0.1700
Data Index: 5149615 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8917. Min Act: -0.1700
Data Index: 8372327 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8917. Min Act: -0.1700
Data Index: 4645133 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8917. Min Act: -0.1700
Data Index: 5638819 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8605. Min Act: -0.1700
Data Index: 8162646 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8605. Min Act: -0.1700
Data Index: 1580337 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8605. Min Act: -0.1700
Data Index: 5508313 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 8541946 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8605. Min Act: -0.1700
Data Index: 2343767 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.7980. Min Act: -0.1700
Data Index: 4407055 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8605. Min Act: -0.1700
Data Index: 617134 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 6939962 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4542. Min Range: -6.4542
Max Act: 5.7667. Min Act: -0.1700
Data Index: 5406990 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19