Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.5793. Min Act: -0.1700
Data Index: 651730 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.5168. Min Act: -0.1700
Data Index: 8083359 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.4543. Min Act: -0.1700
Data Index: 3065453 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.4543. Min Act: -0.1700
Data Index: 4070317 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.3918. Min Act: -0.1700
Data Index: 973722 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.3293. Min Act: -0.1700
Data Index: 1503182 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.2668. Min Act: -0.1700
Data Index: 6483496 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.3293. Min Act: -0.1700
Data Index: 6274014 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.2043. Min Act: -0.1700
Data Index: 4030814 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.0793. Min Act: -0.1700
Data Index: 7293153 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.0793. Min Act: -0.1700
Data Index: 7442632 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.0168. Min Act: -0.1700
Data Index: 3865420 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.0168. Min Act: -0.1700
Data Index: 1620091 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5793. Min Range: -8.5793
Max Act: 8.0168. Min Act: -0.1700
Data Index: 8590204 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5793. Min Range: -8.5793
Max Act: 7.9543. Min Act: -0.1700
Data Index: 8041731 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5793. Min Range: -8.5793
Max Act: 7.9543. Min Act: -0.1700
Data Index: 4289951 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5793. Min Range: -8.5793
Max Act: 7.9543. Min Act: -0.1700
Data Index: 7120605 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5793. Min Range: -8.5793
Max Act: 7.8918. Min Act: -0.1700
Data Index: 6245451 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5793. Min Range: -8.5793
Max Act: 7.8918. Min Act: -0.1700
Data Index: 7888023 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5793. Min Range: -8.5793
Max Act: 7.8918. Min Act: -0.1700
Data Index: 5267569 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19