Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1207 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.3677. Min Act: -0.1700
Data Index: 6869550 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.2426. Min Act: -0.1700
Data Index: 4147510 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.2114. Min Act: -0.1700
Data Index: 8437945 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.1801. Min Act: -0.1700
Data Index: 3254441 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0864. Min Act: -0.1700
Data Index: 3041093 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.1176. Min Act: -0.1700
Data Index: 614320 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.1489. Min Act: -0.1700
Data Index: 4017529 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0551. Min Act: -0.1700
Data Index: 7084602 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.1176. Min Act: -0.1700
Data Index: 4133860 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0864. Min Act: -0.1700
Data Index: 6898378 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0551. Min Act: -0.1700
Data Index: 6652485 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0551. Min Act: -0.1700
Data Index: 3729847 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0551. Min Act: -0.1700
Data Index: 4369263 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0551. Min Act: -0.1700
Data Index: 7582686 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0238. Min Act: -0.1700
Data Index: 3633720 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0238. Min Act: -0.1700
Data Index: 1256843 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0238. Min Act: -0.1700
Data Index: 2446207 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3677. Min Range: -4.3677
Max Act: 3.9926. Min Act: -0.1700
Data Index: 603928 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3677. Min Range: -4.3677
Max Act: 4.0238. Min Act: -0.1700
Data Index: 148869 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3677. Min Range: -4.3677
Max Act: 3.9926. Min Act: -0.1700
Data Index: 1844350 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19