Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5289 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.9473. Min Act: -0.1700
Data Index: 3464017 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.8848. Min Act: -0.1700
Data Index: 2020914 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.8848. Min Act: -0.1700
Data Index: 4819617 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.8848. Min Act: -0.1700
Data Index: 8634318 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.8536. Min Act: -0.1700
Data Index: 2641859 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.8223. Min Act: -0.1700
Data Index: 4812907 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.8223. Min Act: -0.1700
Data Index: 1258816 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.7598. Min Act: -0.1700
Data Index: 6057205 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.6348. Min Act: -0.1700
Data Index: 4547119 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.6348. Min Act: -0.1700
Data Index: 4819616 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.6036. Min Act: -0.1700
Data Index: 3954377 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.6036. Min Act: -0.1700
Data Index: 3166230 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.5723. Min Act: -0.1700
Data Index: 4094290 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.5411. Min Act: -0.1700
Data Index: 2209588 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.5723. Min Act: -0.1700
Data Index: 1521812 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.5411. Min Act: -0.1700
Data Index: 158172 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.5411. Min Act: -0.1700
Data Index: 8625415 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.5098. Min Act: -0.1700
Data Index: 6550639 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.4786. Min Act: -0.1700
Data Index: 5444636 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9473. Min Range: -5.9473
Max Act: 5.4786. Min Act: -0.1700
Data Index: 7896123 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19