Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.8566. Min Act: -0.1700
Data Index: 2656294 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.4816. Min Act: -0.1700
Data Index: 3306726 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.4503. Min Act: -0.1700
Data Index: 5700244 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.3878. Min Act: -0.1700
Data Index: 5925402 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.3878. Min Act: -0.1700
Data Index: 827468 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.3566. Min Act: -0.1700
Data Index: 343203 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.2941. Min Act: -0.1700
Data Index: 7477923 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.2941. Min Act: -0.1700
Data Index: 2124791 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.2941. Min Act: -0.1700
Data Index: 1189423 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.2628. Min Act: -0.1700
Data Index: 728318 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.2316. Min Act: -0.1700
Data Index: 7216457 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.2003. Min Act: -0.1700
Data Index: 4733486 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.1378. Min Act: -0.1700
Data Index: 8065320 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.1066. Min Act: -0.1700
Data Index: 1910663 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.1066. Min Act: -0.1700
Data Index: 8823685 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.1066. Min Act: -0.1700
Data Index: 2008751 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.1066. Min Act: -0.1700
Data Index: 6755067 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.0441. Min Act: -0.1700
Data Index: 4275336 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.0753. Min Act: -0.1700
Data Index: 2153071 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8566. Min Range: -6.8566
Max Act: 6.0441. Min Act: -0.1700
Data Index: 7460757 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19