Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3201 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2281. Min Range: -7.2281
Max Act: 7.2281. Min Act: -0.1700
Data Index: 143213 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2281. Min Range: -7.2281
Max Act: 7.1656. Min Act: -0.1700
Data Index: 4366217 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2281. Min Range: -7.2281
Max Act: 7.1031. Min Act: -0.1700
Data Index: 2380632 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2281. Min Range: -7.2281
Max Act: 7.1031. Min Act: -0.1700
Data Index: 3318974 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2281. Min Range: -7.2281
Max Act: 7.0719. Min Act: -0.1700
Data Index: 5478769 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2281. Min Range: -7.2281
Max Act: 7.0406. Min Act: -0.1700
Data Index: 729345 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2281. Min Range: -7.2281
Max Act: 7.0406. Min Act: -0.1700
Data Index: 3893548 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2281. Min Range: -7.2281
Max Act: 7.0094. Min Act: -0.1700
Data Index: 2860372 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.9469. Min Act: -0.1700
Data Index: 3144372 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.9781. Min Act: -0.1700
Data Index: 1924722 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.9781. Min Act: -0.1700
Data Index: 3357367 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.9469. Min Act: -0.1700
Data Index: 237219 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.9469. Min Act: -0.1700
Data Index: 6190493 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.9156. Min Act: -0.1700
Data Index: 1370171 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.8844. Min Act: -0.1700
Data Index: 4029873 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.8531. Min Act: -0.1700
Data Index: 5881337 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.8844. Min Act: -0.1700
Data Index: 6891417 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.8844. Min Act: -0.1700
Data Index: 6621730 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.8531. Min Act: -0.1700
Data Index: 933221 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2281. Min Range: -7.2281
Max Act: 6.8531. Min Act: -0.1700
Data Index: 6224669 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19