Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.3407. Min Act: -0.1700
Data Index: 2512223 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.3094. Min Act: -0.1700
Data Index: 6222910 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.2782. Min Act: -0.1700
Data Index: 5160944 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.1844. Min Act: -0.1700
Data Index: 2327097 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.1532. Min Act: -0.1700
Data Index: 7035166 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.1844. Min Act: -0.1700
Data Index: 975787 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.1219. Min Act: -0.1700
Data Index: 2992016 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.1219. Min Act: -0.1700
Data Index: 3572415 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.0907. Min Act: -0.1700
Data Index: 5593351 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.0907. Min Act: -0.1700
Data Index: 8177483 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.0907. Min Act: -0.1700
Data Index: 287404 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.0907. Min Act: -0.1700
Data Index: 3109313 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.0282. Min Act: -0.1700
Data Index: 6044955 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.0282. Min Act: -0.1700
Data Index: 5476012 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.0282. Min Act: -0.1700
Data Index: 8114517 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.0282. Min Act: -0.1700
Data Index: 3673474 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3407. Min Range: -6.3407
Max Act: 6.0282. Min Act: -0.1700
Data Index: 8640581 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3407. Min Range: -6.3407
Max Act: 5.9969. Min Act: -0.1700
Data Index: 7096334 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3407. Min Range: -6.3407
Max Act: 5.9969. Min Act: -0.1700
Data Index: 5055806 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3407. Min Range: -6.3407
Max Act: 5.9969. Min Act: -0.1700
Data Index: 3631625 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19