Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.6555. Min Act: -0.1700
Data Index: 5927447 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4989. Min Act: -0.1700
Data Index: 4249949 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4989. Min Act: -0.1700
Data Index: 2974002 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4989. Min Act: -0.1700
Data Index: 1362719 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4519. Min Act: -0.1700
Data Index: 3908201 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4833. Min Act: -0.1700
Data Index: 7418742 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4833. Min Act: -0.1700
Data Index: 3864560 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4833. Min Act: -0.1700
Data Index: 7258291 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4519. Min Act: -0.1700
Data Index: 6030366 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4206. Min Act: -0.1700
Data Index: 6769204 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4363. Min Act: -0.1700
Data Index: 4649079 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4519. Min Act: -0.1700
Data Index: 6462732 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4206. Min Act: -0.1700
Data Index: 6849751 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4049. Min Act: -0.1700
Data Index: 4730471 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.3892. Min Act: -0.1700
Data Index: 2118102 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4206. Min Act: -0.1700
Data Index: 8409702 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.4363. Min Act: -0.1700
Data Index: 751157 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.3735. Min Act: -0.1700
Data Index: 4688491 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.3735. Min Act: -0.1700
Data Index: 3645269 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6555. Min Range: -3.6555
Max Act: 3.3892. Min Act: -0.1700
Data Index: 3948025 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19