Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.8344. Min Act: -0.1700
Data Index: 5648852 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6469. Min Act: -0.1700
Data Index: 7031296 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6469. Min Act: -0.1700
Data Index: 2099566 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6156. Min Act: -0.1700
Data Index: 6417002 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6156. Min Act: -0.1700
Data Index: 7294961 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6156. Min Act: -0.1700
Data Index: 249267 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6156. Min Act: -0.1700
Data Index: 357577 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6156. Min Act: -0.1700
Data Index: 6757091 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6156. Min Act: -0.1700
Data Index: 6569834 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6156. Min Act: -0.1700
Data Index: 8316385 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5844. Min Act: -0.1700
Data Index: 5130856 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5531. Min Act: -0.1700
Data Index: 2345381 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5844. Min Act: -0.1700
Data Index: 3551042 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5844. Min Act: -0.1700
Data Index: 2174342 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5844. Min Act: -0.1700
Data Index: 2328756 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5531. Min Act: -0.1700
Data Index: 6796390 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5531. Min Act: -0.1700
Data Index: 2154575 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5844. Min Act: -0.1700
Data Index: 5914607 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5219. Min Act: -0.1700
Data Index: 1689684 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5531. Min Act: -0.1700
Data Index: 429837 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19