Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.6829. Min Act: -0.1700
Data Index: 8402798 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.6829. Min Act: -0.1700
Data Index: 2005332 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.6204. Min Act: -0.1700
Data Index: 1366871 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5891. Min Act: -0.1700
Data Index: 1677390 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5891. Min Act: -0.1700
Data Index: 3959224 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.6204. Min Act: -0.1700
Data Index: 4393517 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5891. Min Act: -0.1700
Data Index: 7941749 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5891. Min Act: -0.1700
Data Index: 5418773 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5579. Min Act: -0.1700
Data Index: 1002765 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5579. Min Act: -0.1700
Data Index: 6349544 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5579. Min Act: -0.1700
Data Index: 4300761 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5891. Min Act: -0.1700
Data Index: 3910716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5266. Min Act: -0.1700
Data Index: 5681400 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5266. Min Act: -0.1700
Data Index: 1222886 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5266. Min Act: -0.1700
Data Index: 1491024 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5266. Min Act: -0.1700
Data Index: 1387583 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.4954. Min Act: -0.1700
Data Index: 5468709 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.4954. Min Act: -0.1700
Data Index: 576579 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.4954. Min Act: -0.1700
Data Index: 4753640 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6829. Min Range: -4.6829
Max Act: 4.5266. Min Act: -0.1700
Data Index: 1510836 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19