Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3168 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.3986. Min Act: -0.1700
Data Index: 2597888 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.3986. Min Act: -0.1700
Data Index: 7405189 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.3673. Min Act: -0.1700
Data Index: 1490253 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.3048. Min Act: -0.1700
Data Index: 1711179 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.2423. Min Act: -0.1700
Data Index: 920219 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.2111. Min Act: -0.1700
Data Index: 2240493 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.1798. Min Act: -0.1700
Data Index: 5626966 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.1798. Min Act: -0.1700
Data Index: 6350296 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.1173. Min Act: -0.1700
Data Index: 6954231 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.0861. Min Act: -0.1700
Data Index: 5072160 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.0861. Min Act: -0.1700
Data Index: 2730312 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.0548. Min Act: -0.1700
Data Index: 3233662 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.0548. Min Act: -0.1700
Data Index: 626834 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3986. Min Range: -7.3986
Max Act: 7.0548. Min Act: -0.1700
Data Index: 8687026 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3986. Min Range: -7.3986
Max Act: 6.9923. Min Act: -0.1700
Data Index: 5066271 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3986. Min Range: -7.3986
Max Act: 6.9611. Min Act: -0.1700
Data Index: 2006238 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3986. Min Range: -7.3986
Max Act: 6.9611. Min Act: -0.1700
Data Index: 7253473 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3986. Min Range: -7.3986
Max Act: 6.8986. Min Act: -0.1700
Data Index: 2532264 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3986. Min Range: -7.3986
Max Act: 6.8986. Min Act: -0.1700
Data Index: 64376 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3986. Min Range: -7.3986
Max Act: 6.8986. Min Act: -0.1700
Data Index: 405342 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19