Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2004. Min Range: -7.2004
Max Act: 7.2004. Min Act: -0.1700
Data Index: 5162385 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2004. Min Range: -7.2004
Max Act: 7.1379. Min Act: -0.1700
Data Index: 5236656 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2004. Min Range: -7.2004
Max Act: 7.0129. Min Act: -0.1700
Data Index: 2502254 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.9816. Min Act: -0.1700
Data Index: 4629913 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.9191. Min Act: -0.1700
Data Index: 7692358 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.8879. Min Act: -0.1700
Data Index: 7000149 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.8566. Min Act: -0.1700
Data Index: 4447868 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.8566. Min Act: -0.1700
Data Index: 430223 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.8254. Min Act: -0.1700
Data Index: 3609089 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.8254. Min Act: -0.1700
Data Index: 4274200 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.7941. Min Act: -0.1700
Data Index: 321953 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.7941. Min Act: -0.1700
Data Index: 6597403 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.8254. Min Act: -0.1700
Data Index: 3223761 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.7941. Min Act: -0.1700
Data Index: 5692003 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.7629. Min Act: -0.1700
Data Index: 5142664 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.7316. Min Act: -0.1700
Data Index: 5372026 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.7004. Min Act: -0.1700
Data Index: 7402184 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.7316. Min Act: -0.1700
Data Index: 1466388 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.7629. Min Act: -0.1700
Data Index: 1355435 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2004. Min Range: -7.2004
Max Act: 6.7004. Min Act: -0.1700
Data Index: 5372010 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19