Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 375 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.8817. Min Act: -0.1700
Data Index: 5560055 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.7879. Min Act: -0.1700
Data Index: 3583473 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.7879. Min Act: -0.1700
Data Index: 410825 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.8192. Min Act: -0.1700
Data Index: 8227865 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.7567. Min Act: -0.1700
Data Index: 1515839 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.7254. Min Act: -0.1700
Data Index: 3039123 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.6942. Min Act: -0.1700
Data Index: 8383496 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.6629. Min Act: -0.1700
Data Index: 5120271 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.6629. Min Act: -0.1700
Data Index: 6860442 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.6629. Min Act: -0.1700
Data Index: 682899 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.6629. Min Act: -0.1700
Data Index: 8227333 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.6629. Min Act: -0.1700
Data Index: 2051630 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.6317. Min Act: -0.1700
Data Index: 5798792 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.6004. Min Act: -0.1700
Data Index: 6745275 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.5692. Min Act: -0.1700
Data Index: 4949802 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.5692. Min Act: -0.1700
Data Index: 1012752 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.6004. Min Act: -0.1700
Data Index: 1980146 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.5692. Min Act: -0.1700
Data Index: 3039120 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.5692. Min Act: -0.1700
Data Index: 3736302 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8817. Min Range: -5.8817
Max Act: 5.5379. Min Act: -0.1700
Data Index: 3039121 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19