Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3838 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.3111. Min Act: -0.1700
Data Index: 8363993 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.2325. Min Act: -0.1700
Data Index: 5827549 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.2011. Min Act: -0.1700
Data Index: 1167912 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.1696. Min Act: -0.1700
Data Index: 2472025 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0909. Min Act: -0.1700
Data Index: 4964460 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.1066. Min Act: -0.1700
Data Index: 4448342 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0751. Min Act: -0.1700
Data Index: 8267284 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0593. Min Act: -0.1700
Data Index: 8424387 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0593. Min Act: -0.1700
Data Index: 5724590 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0593. Min Act: -0.1700
Data Index: 6357794 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0436. Min Act: -0.1700
Data Index: 5041327 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0278. Min Act: -0.1700
Data Index: 3923522 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0278. Min Act: -0.1700
Data Index: 3704697 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0278. Min Act: -0.1700
Data Index: 6876322 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0278. Min Act: -0.1700
Data Index: 4642002 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0120. Min Act: -0.1700
Data Index: 1357613 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3111. Min Range: -3.3111
Max Act: 2.9962. Min Act: -0.1700
Data Index: 896640 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0120. Min Act: -0.1700
Data Index: 4488999 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3111. Min Range: -3.3111
Max Act: 2.9962. Min Act: -0.1700
Data Index: 520690 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3111. Min Range: -3.3111
Max Act: 3.0278. Min Act: -0.1700
Data Index: 7928968 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19