Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.9486. Min Act: -0.1700
Data Index: 1205023 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.8861. Min Act: -0.1700
Data Index: 672597 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.8236. Min Act: -0.1700
Data Index: 6098281 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.8236. Min Act: -0.1700
Data Index: 555340 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.8236. Min Act: -0.1700
Data Index: 4807389 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.7924. Min Act: -0.1700
Data Index: 1611388 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.7611. Min Act: -0.1700
Data Index: 3562236 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.7299. Min Act: -0.1700
Data Index: 638824 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.7299. Min Act: -0.1700
Data Index: 4807390 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.7299. Min Act: -0.1700
Data Index: 1472263 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.7299. Min Act: -0.1700
Data Index: 2252333 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.7611. Min Act: -0.1700
Data Index: 297264 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.7299. Min Act: -0.1700
Data Index: 1205022 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.7299. Min Act: -0.1700
Data Index: 2841858 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.6986. Min Act: -0.1697
Data Index: 7426808 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.6986. Min Act: -0.1700
Data Index: 861192 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.6986. Min Act: -0.1700
Data Index: 7906840 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.6986. Min Act: -0.1700
Data Index: 2640519 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.6986. Min Act: -0.1700
Data Index: 5250345 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9486. Min Range: -4.9486
Max Act: 4.6986. Min Act: -0.1700
Data Index: 3111374 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19