Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 942 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0227. Min Range: -5.0227
Max Act: 5.0227. Min Act: -0.1700
Data Index: 6190664 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.9914. Min Act: -0.1700
Data Index: 2879516 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.9602. Min Act: -0.1700
Data Index: 3796618 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.8352. Min Act: -0.1700
Data Index: 3549008 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.8039. Min Act: -0.1700
Data Index: 1231696 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.7727. Min Act: -0.1700
Data Index: 6107937 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.7727. Min Act: -0.1700
Data Index: 357185 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.7727. Min Act: -0.1700
Data Index: 7542887 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.7727. Min Act: -0.1700
Data Index: 7469593 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.7414. Min Act: -0.1700
Data Index: 6560559 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.7102. Min Act: -0.1700
Data Index: 6326998 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.7102. Min Act: -0.1700
Data Index: 689910 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.6789. Min Act: -0.1700
Data Index: 4462597 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.6477. Min Act: -0.1700
Data Index: 2861986 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.6477. Min Act: -0.1700
Data Index: 357169 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.6477. Min Act: -0.1700
Data Index: 7882658 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.6477. Min Act: -0.1700
Data Index: 6656132 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.6477. Min Act: -0.1700
Data Index: 357183 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.5852. Min Act: -0.1700
Data Index: 1997825 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0227. Min Range: -5.0227
Max Act: 4.5852. Min Act: -0.1700
Data Index: 1231697 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19