Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3802. Min Range: -5.3802
Max Act: 5.3802. Min Act: -0.1700
Data Index: 5435954 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3802. Min Range: -5.3802
Max Act: 5.2239. Min Act: -0.1700
Data Index: 5729667 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3802. Min Range: -5.3802
Max Act: 5.1614. Min Act: -0.1700
Data Index: 6396681 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3802. Min Range: -5.3802
Max Act: 5.0989. Min Act: -0.1700
Data Index: 3190394 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3802. Min Range: -5.3802
Max Act: 5.0677. Min Act: -0.1700
Data Index: 629007 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3802. Min Range: -5.3802
Max Act: 5.0364. Min Act: -0.1700
Data Index: 5402174 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3802. Min Range: -5.3802
Max Act: 5.0052. Min Act: -0.1700
Data Index: 5511116 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.9739. Min Act: -0.1700
Data Index: 5809256 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.9114. Min Act: -0.1700
Data Index: 7813781 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.8802. Min Act: -0.1700
Data Index: 7133721 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.9114. Min Act: -0.1700
Data Index: 8120662 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.8802. Min Act: -0.1700
Data Index: 7349066 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.8802. Min Act: -0.1700
Data Index: 7318537 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.7864. Min Act: -0.1700
Data Index: 4318716 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.8177. Min Act: -0.1700
Data Index: 2913008 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.8177. Min Act: -0.1700
Data Index: 3043659 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.8177. Min Act: -0.1700
Data Index: 2412359 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.8177. Min Act: -0.1700
Data Index: 4634600 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.8177. Min Act: -0.1700
Data Index: 5656466 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3802. Min Range: -5.3802
Max Act: 4.7864. Min Act: -0.1700
Data Index: 2648424 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19