Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1005. Min Range: -8.1005
Max Act: 8.1005. Min Act: -0.1700
Data Index: 518122 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.9755. Min Act: -0.1700
Data Index: 4779416 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.8193. Min Act: -0.1700
Data Index: 5979586 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.8193. Min Act: -0.1700
Data Index: 5979584 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.8193. Min Act: -0.1700
Data Index: 6819960 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.7880. Min Act: -0.1700
Data Index: 2370385 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.7880. Min Act: -0.1700
Data Index: 988353 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.7255. Min Act: -0.1700
Data Index: 5979590 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.6630. Min Act: -0.1700
Data Index: 5239792 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.6318. Min Act: -0.1700
Data Index: 5979585 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.6318. Min Act: -0.1700
Data Index: 1124534 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.6318. Min Act: -0.1700
Data Index: 1616755 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.6005. Min Act: -0.1700
Data Index: 4777128 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.5380. Min Act: -0.1700
Data Index: 5095290 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.5068. Min Act: -0.1700
Data Index: 6521400 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.5380. Min Act: -0.1700
Data Index: 5095193 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.5068. Min Act: -0.1700
Data Index: 5979592 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.4443. Min Act: -0.1700
Data Index: 5337662 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.4443. Min Act: -0.1700
Data Index: 6921558 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1005. Min Range: -8.1005
Max Act: 7.4130. Min Act: -0.1700
Data Index: 5979580 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19