Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.2166. Min Act: -0.1700
Data Index: 6230405 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.2166. Min Act: -0.1700
Data Index: 6157660 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.1854. Min Act: -0.1700
Data Index: 5425355 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.1541. Min Act: -0.1700
Data Index: 476898 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.1541. Min Act: -0.1700
Data Index: 5755571 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.1229. Min Act: -0.1700
Data Index: 1268571 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.1229. Min Act: -0.1700
Data Index: 903656 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.1541. Min Act: -0.1700
Data Index: 4739885 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.0916. Min Act: -0.1700
Data Index: 8221980 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.0604. Min Act: -0.1700
Data Index: 3311234 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2166. Min Range: -5.2166
Max Act: 4.9979. Min Act: -0.1700
Data Index: 1989246 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2166. Min Range: -5.2166
Max Act: 5.0291. Min Act: -0.1700
Data Index: 1415807 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2166. Min Range: -5.2166
Max Act: 4.9979. Min Act: -0.1700
Data Index: 360887 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2166. Min Range: -5.2166
Max Act: 4.9666. Min Act: -0.1700
Data Index: 2965046 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2166. Min Range: -5.2166
Max Act: 4.9666. Min Act: -0.1700
Data Index: 442386 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2166. Min Range: -5.2166
Max Act: 4.9354. Min Act: -0.1700
Data Index: 6132838 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2166. Min Range: -5.2166
Max Act: 4.9666. Min Act: -0.1700
Data Index: 2381179 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2166. Min Range: -5.2166
Max Act: 4.9666. Min Act: -0.1700
Data Index: 1705837 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2166. Min Range: -5.2166
Max Act: 4.9666. Min Act: -0.1700
Data Index: 3348601 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2166. Min Range: -5.2166
Max Act: 4.9666. Min Act: -0.1700
Data Index: 5749006 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19