Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4745 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.4826. Min Act: -0.1700
Data Index: 4535640 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.3576. Min Act: -0.1700
Data Index: 299419 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.2951. Min Act: -0.1700
Data Index: 7941927 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.2326. Min Act: -0.1700
Data Index: 3344837 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.2326. Min Act: -0.1700
Data Index: 7419343 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.1701. Min Act: -0.1700
Data Index: 1478493 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.1076. Min Act: -0.1700
Data Index: 4226845 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.1076. Min Act: -0.1700
Data Index: 3446029 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.1701. Min Act: -0.1700
Data Index: 175659 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4826. Min Range: -9.4826
Max Act: 9.0451. Min Act: -0.1700
Data Index: 8686051 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.9826. Min Act: -0.1700
Data Index: 1050782 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.9826. Min Act: -0.1700
Data Index: 5556603 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.9826. Min Act: -0.1700
Data Index: 6272211 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.9201. Min Act: -0.1700
Data Index: 4056776 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.9201. Min Act: -0.1700
Data Index: 3706484 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.9201. Min Act: -0.1700
Data Index: 476259 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.9201. Min Act: -0.1700
Data Index: 2198604 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.8576. Min Act: -0.1700
Data Index: 2195568 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.8576. Min Act: -0.1700
Data Index: 5750639 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4826. Min Range: -9.4826
Max Act: 8.8576. Min Act: -0.1700
Data Index: 3321736 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19