Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.9320. Min Act: -0.1700
Data Index: 7114692 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.8526. Min Act: -0.1700
Data Index: 3639526 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.7890. Min Act: -0.1700
Data Index: 849553 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.7731. Min Act: -0.1700
Data Index: 2066068 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.7411. Min Act: -0.1700
Data Index: 3340469 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.7252. Min Act: -0.1700
Data Index: 6099187 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.7252. Min Act: -0.1700
Data Index: 3615683 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.7092. Min Act: -0.1700
Data Index: 466724 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6932. Min Act: -0.1700
Data Index: 8521643 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.7092. Min Act: -0.1700
Data Index: 474029 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6772. Min Act: -0.1700
Data Index: 4703988 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6611. Min Act: -0.1700
Data Index: 4018646 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6772. Min Act: -0.1700
Data Index: 3717347 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6772. Min Act: -0.1700
Data Index: 371056 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6611. Min Act: -0.1700
Data Index: 7869631 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6932. Min Act: -0.1700
Data Index: 1956782 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6611. Min Act: -0.1700
Data Index: 2970433 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6611. Min Act: -0.1700
Data Index: 3164939 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6451. Min Act: -0.1700
Data Index: 1629646 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9320. Min Range: -2.9320
Max Act: 2.6451. Min Act: -0.1700
Data Index: 2643533 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19