Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.3084. Min Act: -0.1700
Data Index: 344138 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.2146. Min Act: -0.1700
Data Index: 3352706 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.2146. Min Act: -0.1700
Data Index: 3664505 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1834. Min Act: -0.1700
Data Index: 1205141 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1834. Min Act: -0.1700
Data Index: 4503444 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1521. Min Act: -0.1700
Data Index: 1713493 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1521. Min Act: -0.1700
Data Index: 8496655 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1209. Min Act: -0.1700
Data Index: 4989967 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1209. Min Act: -0.1700
Data Index: 2924656 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1209. Min Act: -0.1700
Data Index: 4435109 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1209. Min Act: -0.1700
Data Index: 3591187 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1209. Min Act: -0.1700
Data Index: 1140000 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1209. Min Act: -0.1700
Data Index: 4814899 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.1209. Min Act: -0.1700
Data Index: 99623 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.0896. Min Act: -0.1700
Data Index: 35132 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.0584. Min Act: -0.1700
Data Index: 3146786 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.0896. Min Act: -0.1700
Data Index: 6966111 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.0896. Min Act: -0.1700
Data Index: 1698085 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.0896. Min Act: -0.1700
Data Index: 4989966 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3084. Min Range: -5.3084
Max Act: 5.0584. Min Act: -0.1700
Data Index: 5848446 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19