Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.9979. Min Act: -0.1700
Data Index: 2948274 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.7791. Min Act: -0.1700
Data Index: 2874670 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.7479. Min Act: -0.1700
Data Index: 8562279 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.6541. Min Act: -0.1700
Data Index: 5357910 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.7166. Min Act: -0.1700
Data Index: 7770721 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.6541. Min Act: -0.1700
Data Index: 274184 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.6229. Min Act: -0.1700
Data Index: 484756 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.5916. Min Act: -0.1700
Data Index: 1828286 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.5916. Min Act: -0.1700
Data Index: 5541278 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.4041. Min Act: -0.1700
Data Index: 6361192 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.4041. Min Act: -0.1700
Data Index: 3955406 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.4041. Min Act: -0.1700
Data Index: 4369424 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.4354. Min Act: -0.1700
Data Index: 4479058 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.3104. Min Act: -0.1700
Data Index: 6152526 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.3104. Min Act: -0.1700
Data Index: 1691202 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.3104. Min Act: -0.1700
Data Index: 42410 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.2791. Min Act: -0.1700
Data Index: 1023362 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.3104. Min Act: -0.1700
Data Index: 102771 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.3104. Min Act: -0.1700
Data Index: 2113813 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9979. Min Range: -6.9979
Max Act: 6.3104. Min Act: -0.1700
Data Index: 1035488 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19