Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2379 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.5121. Min Act: -0.1700
Data Index: 948538 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.4808. Min Act: -0.1700
Data Index: 7618258 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.4183. Min Act: -0.1700
Data Index: 5079044 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.3558. Min Act: -0.1700
Data Index: 6284548 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.3246. Min Act: -0.1700
Data Index: 25603 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.3246. Min Act: -0.1700
Data Index: 679710 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.2308. Min Act: -0.1700
Data Index: 4289392 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.2621. Min Act: -0.1700
Data Index: 6311806 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.2308. Min Act: -0.1700
Data Index: 8772027 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.2308. Min Act: -0.1700
Data Index: 6529414 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1996. Min Act: -0.1700
Data Index: 4790894 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1996. Min Act: -0.1700
Data Index: 3554107 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1996. Min Act: -0.1700
Data Index: 8233103 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1996. Min Act: -0.1700
Data Index: 2645460 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1683. Min Act: -0.1700
Data Index: 6162012 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1683. Min Act: -0.1700
Data Index: 2302423 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1683. Min Act: -0.1700
Data Index: 5178891 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1996. Min Act: -0.1700
Data Index: 4038121 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1371. Min Act: -0.1700
Data Index: 7539484 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5121. Min Range: -6.5121
Max Act: 6.1371. Min Act: -0.1700
Data Index: 1601527 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19