Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5482 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.8355. Min Act: -0.1700
Data Index: 1947192 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.7730. Min Act: -0.1700
Data Index: 6560538 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.7418. Min Act: -0.1700
Data Index: 6560525 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.7418. Min Act: -0.1700
Data Index: 7202546 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.6168. Min Act: -0.1700
Data Index: 6196994 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.6168. Min Act: -0.1700
Data Index: 7940650 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.6168. Min Act: -0.1700
Data Index: 6560532 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.5855. Min Act: -0.1700
Data Index: 6560534 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.5543. Min Act: -0.1700
Data Index: 4619782 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.5543. Min Act: -0.1700
Data Index: 7732397 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.5230. Min Act: -0.1700
Data Index: 7802239 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4918. Min Act: -0.1700
Data Index: 3568720 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4918. Min Act: -0.1700
Data Index: 4777326 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4605. Min Act: -0.1700
Data Index: 527731 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4605. Min Act: -0.1700
Data Index: 7072908 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4605. Min Act: -0.1700
Data Index: 6196990 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4605. Min Act: -0.1700
Data Index: 4345473 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4293. Min Act: -0.1700
Data Index: 5924899 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4293. Min Act: -0.1700
Data Index: 6560536 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4293. Min Act: -0.1700
Data Index: 499321 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19