Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1692 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.9722. Min Act: -0.1700
Data Index: 5701108 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.9409. Min Act: -0.1700
Data Index: 2494265 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.8472. Min Act: -0.1700
Data Index: 7187468 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.6284. Min Act: -0.1700
Data Index: 1510826 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5659. Min Act: -0.1700
Data Index: 3458921 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5347. Min Act: -0.1700
Data Index: 4968472 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.5347. Min Act: -0.1700
Data Index: 6603910 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.4722. Min Act: -0.1700
Data Index: 630479 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.4722. Min Act: -0.1700
Data Index: 3890121 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.4722. Min Act: -0.1700
Data Index: 8687130 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.4409. Min Act: -0.1700
Data Index: 5124158 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.4409. Min Act: -0.1700
Data Index: 1765798 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.4409. Min Act: -0.1700
Data Index: 3909805 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.4097. Min Act: -0.1700
Data Index: 7510905 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.3784. Min Act: -0.1700
Data Index: 4415712 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.3784. Min Act: -0.1700
Data Index: 731166 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.3784. Min Act: -0.1700
Data Index: 3093478 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.3784. Min Act: -0.1700
Data Index: 1518476 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.3784. Min Act: -0.1700
Data Index: 2884563 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9722. Min Range: -5.9722
Max Act: 5.3784. Min Act: -0.1700
Data Index: 3814002 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19