Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2204. Min Range: -8.2204
Max Act: 8.1579. Min Act: -0.1700
Data Index: 643423 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2204. Min Range: -8.2204
Max Act: 8.2204. Min Act: -0.1700
Data Index: 8814489 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2204. Min Range: -8.2204
Max Act: 8.1579. Min Act: -0.1700
Data Index: 3717660 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.9079. Min Act: -0.1700
Data Index: 5119470 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.8454. Min Act: -0.1700
Data Index: 8591388 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.8454. Min Act: -0.1700
Data Index: 6960479 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.7204. Min Act: -0.1700
Data Index: 7816075 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.6579. Min Act: -0.1700
Data Index: 2468532 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.5329. Min Act: -0.1700
Data Index: 2061876 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.5329. Min Act: -0.1700
Data Index: 5058153 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.4704. Min Act: -0.1700
Data Index: 6320358 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.4704. Min Act: -0.1700
Data Index: 4968912 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.4704. Min Act: -0.1700
Data Index: 539794 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.4392. Min Act: -0.1700
Data Index: 2160566 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.4392. Min Act: -0.1700
Data Index: 3269061 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.3767. Min Act: -0.1700
Data Index: 6974286 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.3767. Min Act: -0.1700
Data Index: 5040660 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.3454. Min Act: -0.1700
Data Index: 2987546 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.3767. Min Act: -0.1700
Data Index: 915411 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2204. Min Range: -8.2204
Max Act: 7.3454. Min Act: -0.1700
Data Index: 4106470 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19