Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6085 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3864. Min Range: -8.3864
Max Act: 8.3864. Min Act: -0.1700
Data Index: 4434480 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3864. Min Range: -8.3864
Max Act: 8.3239. Min Act: -0.1700
Data Index: 4757698 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3864. Min Range: -8.3864
Max Act: 8.1989. Min Act: -0.1700
Data Index: 2355846 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3864. Min Range: -8.3864
Max Act: 8.1989. Min Act: -0.1700
Data Index: 6501927 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3864. Min Range: -8.3864
Max Act: 8.0427. Min Act: -0.1700
Data Index: 687519 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.9489. Min Act: -0.1700
Data Index: 6823355 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.9489. Min Act: -0.1700
Data Index: 8187493 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.8864. Min Act: -0.1700
Data Index: 2246535 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.8864. Min Act: -0.1700
Data Index: 1995327 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.8552. Min Act: -0.1700
Data Index: 1214060 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.8552. Min Act: -0.1700
Data Index: 7121095 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.7614. Min Act: -0.1700
Data Index: 8176365 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.7927. Min Act: -0.1700
Data Index: 5440076 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.7614. Min Act: -0.1700
Data Index: 2046017 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.7302. Min Act: -0.1700
Data Index: 5475022 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.7302. Min Act: -0.1700
Data Index: 6739143 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.6364. Min Act: -0.1700
Data Index: 6039274 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.6364. Min Act: -0.1700
Data Index: 6961203 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.5739. Min Act: -0.1700
Data Index: 5544644 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3864. Min Range: -8.3864
Max Act: 7.5427. Min Act: -0.1700
Data Index: 5902017 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19