Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.1241. Min Act: -0.1700
Data Index: 4916117 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.1241. Min Act: -0.1700
Data Index: 232167 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.0928. Min Act: -0.1700
Data Index: 4569745 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.0928. Min Act: -0.1700
Data Index: 5918133 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.0928. Min Act: -0.1700
Data Index: 2061057 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.0616. Min Act: -0.1700
Data Index: 6376015 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.0616. Min Act: -0.1700
Data Index: 2036128 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.0303. Min Act: -0.1700
Data Index: 4969061 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.0303. Min Act: -0.1700
Data Index: 5523318 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.0303. Min Act: -0.1700
Data Index: 4959898 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1241. Min Range: -6.1241
Max Act: 6.0303. Min Act: -0.1700
Data Index: 5489557 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1241. Min Range: -6.1241
Max Act: 5.9991. Min Act: -0.1700
Data Index: 6791320 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1241. Min Range: -6.1241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 4124094 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1241. Min Range: -6.1241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 4222048 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1241. Min Range: -6.1241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 6004770 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1241. Min Range: -6.1241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 7517754 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1241. Min Range: -6.1241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 7761515 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1241. Min Range: -6.1241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 2208535 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1241. Min Range: -6.1241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 3734354 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1241. Min Range: -6.1241
Max Act: 5.9366. Min Act: -0.1700
Data Index: 1747898 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19