Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 606 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.7266. Min Act: -0.1700
Data Index: 6287453 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5544. Min Act: -0.1700
Data Index: 6276310 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5388. Min Act: -0.1700
Data Index: 4920477 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5231. Min Act: -0.1700
Data Index: 4920479 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5231. Min Act: -0.1700
Data Index: 2004357 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.4918. Min Act: -0.1700
Data Index: 8603174 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.4761. Min Act: -0.1700
Data Index: 7958970 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.4918. Min Act: -0.1700
Data Index: 7958983 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.4761. Min Act: -0.1700
Data Index: 5511452 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.4605. Min Act: -0.1700
Data Index: 7722925 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.4448. Min Act: -0.1700
Data Index: 7858329 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.4134. Min Act: -0.1700
Data Index: 3819917 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.3978. Min Act: -0.1700
Data Index: 70795 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.3978. Min Act: -0.1700
Data Index: 1548575 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.3821. Min Act: -0.1700
Data Index: 8212002 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.3821. Min Act: -0.1700
Data Index: 559722 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.3664. Min Act: -0.1700
Data Index: 260095 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.3664. Min Act: -0.1700
Data Index: 5679723 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.3507. Min Act: -0.1700
Data Index: 3344068 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.3350. Min Act: -0.1700
Data Index: 3126112 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19