Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4896 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.8255. Min Act: -0.1700
Data Index: 4930486 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.5442. Min Act: -0.1700
Data Index: 8346809 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.3880. Min Act: -0.1700
Data Index: 6848721 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.3567. Min Act: -0.1700
Data Index: 1165332 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.3255. Min Act: -0.1700
Data Index: 6758553 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2630. Min Act: -0.1700
Data Index: 5305329 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6059234 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2630. Min Act: -0.1700
Data Index: 5729134 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2630. Min Act: -0.1700
Data Index: 6734675 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2630. Min Act: -0.1700
Data Index: 1286937 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2317. Min Act: -0.1700
Data Index: 3576417 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2630. Min Act: -0.1700
Data Index: 7633530 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2317. Min Act: -0.1700
Data Index: 869904 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2317. Min Act: -0.1700
Data Index: 1906397 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2317. Min Act: -0.1700
Data Index: 1605918 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.2005. Min Act: -0.1700
Data Index: 5277262 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.1692. Min Act: -0.1700
Data Index: 329322 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.1692. Min Act: -0.1700
Data Index: 7177589 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.1692. Min Act: -0.1700
Data Index: 3194231 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8255. Min Range: -5.8255
Max Act: 5.1692. Min Act: -0.1700
Data Index: 5269532 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19