Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3651 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1785. Min Range: -7.1785
Max Act: 7.1785. Min Act: -0.1700
Data Index: 698362 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.8972. Min Act: -0.1700
Data Index: 8135448 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.8035. Min Act: -0.1700
Data Index: 4103396 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.6160. Min Act: -0.1700
Data Index: 1402178 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.5222. Min Act: -0.1700
Data Index: 5357596 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.4910. Min Act: -0.1700
Data Index: 3259869 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.4597. Min Act: -0.1700
Data Index: 1524515 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.3972. Min Act: -0.1700
Data Index: 5366215 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.3347. Min Act: -0.1700
Data Index: 510710 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.3347. Min Act: -0.1700
Data Index: 1172618 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.2410. Min Act: -0.1700
Data Index: 2089767 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.1785. Min Act: -0.1700
Data Index: 6001849 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.1785. Min Act: -0.1700
Data Index: 4955611 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.1472. Min Act: -0.1700
Data Index: 7233833 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.1472. Min Act: -0.1700
Data Index: 4593264 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.1160. Min Act: -0.1700
Data Index: 4145488 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.1472. Min Act: -0.1700
Data Index: 1979795 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.1160. Min Act: -0.1700
Data Index: 8287805 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.0847. Min Act: -0.1700
Data Index: 4937139 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1785. Min Range: -7.1785
Max Act: 6.0847. Min Act: -0.1700
Data Index: 4480767 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19