Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0425. Min Range: -4.0425
Max Act: 4.0425. Min Act: -0.1700
Data Index: 3373274 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0425. Min Range: -4.0425
Max Act: 4.0112. Min Act: -0.1700
Data Index: 8132882 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0425. Min Range: -4.0425
Max Act: 4.0425. Min Act: -0.1700
Data Index: 1032540 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0425. Min Range: -4.0425
Max Act: 4.0112. Min Act: -0.1700
Data Index: 3880965 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.9487. Min Act: -0.1700
Data Index: 7465498 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.9487. Min Act: -0.1700
Data Index: 8221571 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.9175. Min Act: -0.1700
Data Index: 2366346 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.9175. Min Act: -0.1700
Data Index: 4067980 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.8862. Min Act: -0.1700
Data Index: 4500842 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.9175. Min Act: -0.1700
Data Index: 4091089 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.8549. Min Act: -0.1700
Data Index: 2897395 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.8549. Min Act: -0.1700
Data Index: 4241595 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.8549. Min Act: -0.1700
Data Index: 6768820 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.8393. Min Act: -0.1700
Data Index: 4115671 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.8237. Min Act: -0.1700
Data Index: 3246526 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.8080. Min Act: -0.1700
Data Index: 6413010 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.7924. Min Act: -0.1700
Data Index: 7288514 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.8080. Min Act: -0.1700
Data Index: 323701 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.7767. Min Act: -0.1700
Data Index: 3261861 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0425. Min Range: -4.0425
Max Act: 3.7611. Min Act: -0.1700
Data Index: 5372503 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19