Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.8002. Min Act: -0.1700
Data Index: 135173 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.6439. Min Act: -0.1700
Data Index: 1013081 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.6439. Min Act: -0.1700
Data Index: 1214923 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5502. Min Act: -0.1700
Data Index: 4698285 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5502. Min Act: -0.1700
Data Index: 4252296 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5189. Min Act: -0.1700
Data Index: 6034853 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5502. Min Act: -0.1700
Data Index: 7463819 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5502. Min Act: -0.1700
Data Index: 8269529 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.4877. Min Act: -0.1700
Data Index: 458131 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5189. Min Act: -0.1700
Data Index: 2197172 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5189. Min Act: -0.1700
Data Index: 5345658 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5189. Min Act: -0.1700
Data Index: 8505017 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5502. Min Act: -0.1700
Data Index: 2876907 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.5189. Min Act: -0.1700
Data Index: 4807743 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.4877. Min Act: -0.1700
Data Index: 6003121 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.4877. Min Act: -0.1700
Data Index: 122830 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.4877. Min Act: -0.1700
Data Index: 5520682 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.4252. Min Act: -0.1700
Data Index: 5036169 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.4564. Min Act: -0.1700
Data Index: 8754912 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8002. Min Range: -4.8002
Max Act: 4.4564. Min Act: -0.1700
Data Index: 2503199 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19