Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.5459. Min Act: -0.1700
Data Index: 812910 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.3584. Min Act: -0.1700
Data Index: 4472421 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.3272. Min Act: -0.1700
Data Index: 1163074 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.3272. Min Act: -0.1700
Data Index: 4892219 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.2959. Min Act: -0.1700
Data Index: 578352 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.2959. Min Act: -0.1700
Data Index: 3771404 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0772. Min Act: -0.1700
Data Index: 2173699 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.1084. Min Act: -0.1700
Data Index: 183093 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0772. Min Act: -0.1700
Data Index: 8251421 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0772. Min Act: -0.1700
Data Index: 2738386 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0772. Min Act: -0.1700
Data Index: 4551005 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0459. Min Act: -0.1700
Data Index: 1072156 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0459. Min Act: -0.1700
Data Index: 4871476 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0147. Min Act: -0.1700
Data Index: 4475472 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5459. Min Range: -6.5459
Max Act: 5.9834. Min Act: -0.1700
Data Index: 2273655 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0147. Min Act: -0.1700
Data Index: 6311631 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0147. Min Act: -0.1700
Data Index: 3319122 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5459. Min Range: -6.5459
Max Act: 6.0147. Min Act: -0.1700
Data Index: 7079166 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5459. Min Range: -6.5459
Max Act: 5.9834. Min Act: -0.1700
Data Index: 5377323 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5459. Min Range: -6.5459
Max Act: 5.9834. Min Act: -0.1700
Data Index: 3829252 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19