Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 400 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8539. Min Range: -8.8539
Max Act: 8.8539. Min Act: -0.1700
Data Index: 364506 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.6039. Min Act: -0.1700
Data Index: 5292906 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.4789. Min Act: -0.1700
Data Index: 5475769 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.5727. Min Act: -0.1700
Data Index: 8384493 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.4164. Min Act: -0.1700
Data Index: 111625 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.4477. Min Act: -0.1700
Data Index: 5311762 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.3227. Min Act: -0.1700
Data Index: 2367711 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.2289. Min Act: -0.1700
Data Index: 5511737 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.2289. Min Act: -0.1700
Data Index: 6180068 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.1664. Min Act: -0.1700
Data Index: 8138782 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.1352. Min Act: -0.1700
Data Index: 7582547 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.1977. Min Act: -0.1700
Data Index: 3290320 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.1664. Min Act: -0.1700
Data Index: 690944 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.1039. Min Act: -0.1700
Data Index: 4142632 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.0727. Min Act: -0.1700
Data Index: 6936883 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.1039. Min Act: -0.1700
Data Index: 269251 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.1039. Min Act: -0.1700
Data Index: 6937712 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.1039. Min Act: -0.1700
Data Index: 1846451 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.1352. Min Act: -0.1700
Data Index: 1394538 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8539. Min Range: -8.8539
Max Act: 7.0727. Min Act: -0.1700
Data Index: 6363542 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19