Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.9604. Min Act: -0.1700
Data Index: 3586404 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.9604. Min Act: -0.1700
Data Index: 6716476 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.8979. Min Act: -0.1700
Data Index: 5153872 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.8979. Min Act: -0.1700
Data Index: 4742642 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.8667. Min Act: -0.1700
Data Index: 2080845 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.8667. Min Act: -0.1700
Data Index: 4742663 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.8354. Min Act: -0.1700
Data Index: 8779017 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.7729. Min Act: -0.1700
Data Index: 28536 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.7729. Min Act: -0.1700
Data Index: 28523 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.7417. Min Act: -0.1700
Data Index: 2746197 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.7417. Min Act: -0.1700
Data Index: 8484861 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.7417. Min Act: -0.1700
Data Index: 5469012 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.7104. Min Act: -0.1700
Data Index: 5468993 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.7417. Min Act: -0.1700
Data Index: 7221217 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.6792. Min Act: -0.1700
Data Index: 6757535 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.6792. Min Act: -0.1700
Data Index: 6313315 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.7104. Min Act: -0.1700
Data Index: 3010682 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.6479. Min Act: -0.1700
Data Index: 7005750 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.7104. Min Act: -0.1700
Data Index: 7165402 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9604. Min Range: -4.9604
Max Act: 4.6792. Min Act: -0.1700
Data Index: 7503508 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19