Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 519 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7104. Min Range: -6.7104
Max Act: 6.7104. Min Act: -0.1700
Data Index: 4868054 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7104. Min Range: -6.7104
Max Act: 6.1479. Min Act: -0.1700
Data Index: 8776250 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7104. Min Range: -6.7104
Max Act: 6.1166. Min Act: -0.1700
Data Index: 7285486 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7104. Min Range: -6.7104
Max Act: 6.1166. Min Act: -0.1700
Data Index: 3814268 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7104. Min Range: -6.7104
Max Act: 6.0854. Min Act: -0.1700
Data Index: 2881027 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7104. Min Range: -6.7104
Max Act: 6.0854. Min Act: -0.1700
Data Index: 991422 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7104. Min Range: -6.7104
Max Act: 6.0229. Min Act: -0.1700
Data Index: 3827692 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.9916. Min Act: -0.1700
Data Index: 6874766 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.9916. Min Act: -0.1700
Data Index: 8623624 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.9604. Min Act: -0.1700
Data Index: 8471195 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8979. Min Act: -0.1700
Data Index: 2995166 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8979. Min Act: -0.1700
Data Index: 4847903 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8979. Min Act: -0.1700
Data Index: 4179325 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8979. Min Act: -0.1700
Data Index: 6332126 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8979. Min Act: -0.1700
Data Index: 518985 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8979. Min Act: -0.1700
Data Index: 5773947 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8666. Min Act: -0.1700
Data Index: 1070456 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8666. Min Act: -0.1700
Data Index: 6435600 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8666. Min Act: -0.1700
Data Index: 4325577 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7104. Min Range: -6.7104
Max Act: 5.8354. Min Act: -0.1700
Data Index: 8546101 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19