Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3041. Min Range: -12.3041
Max Act: 12.3041. Min Act: -0.1700
Data Index: 7100582 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3041. Min Range: -12.3041
Max Act: 12.3041. Min Act: -0.1700
Data Index: 7816100 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3041. Min Range: -12.3041
Max Act: 12.2416. Min Act: -0.1700
Data Index: 4953565 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3041. Min Range: -12.3041
Max Act: 12.1166. Min Act: -0.1700
Data Index: 7050308 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3041. Min Range: -12.3041
Max Act: 12.1166. Min Act: -0.1700
Data Index: 5106491 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3041. Min Range: -12.3041
Max Act: 12.0541. Min Act: -0.1700
Data Index: 2237832 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3041. Min Range: -12.3041
Max Act: 12.0541. Min Act: -0.1700
Data Index: 2060159 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.9916. Min Act: -0.1700
Data Index: 8134551 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.9291. Min Act: -0.1700
Data Index: 860585 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.9291. Min Act: -0.1700
Data Index: 2509250 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.9291. Min Act: -0.1700
Data Index: 4781801 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.9291. Min Act: -0.1700
Data Index: 7242778 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.9291. Min Act: -0.1700
Data Index: 1923951 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.9291. Min Act: -0.1700
Data Index: 7052718 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.8666. Min Act: -0.1700
Data Index: 6797358 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.8041. Min Act: -0.1700
Data Index: 8048810 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.8041. Min Act: -0.1700
Data Index: 2634890 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.8041. Min Act: -0.1700
Data Index: 6467310 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.7416. Min Act: -0.1700
Data Index: 1484910 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3041. Min Range: -12.3041
Max Act: 11.7416. Min Act: -0.1700
Data Index: 5504478 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19