Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0317. Min Range: -5.0317
Max Act: 5.0317. Min Act: -0.1700
Data Index: 7368403 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0317. Min Range: -5.0317
Max Act: 5.0004. Min Act: -0.1700
Data Index: 6259199 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.9692. Min Act: -0.1700
Data Index: 3247467 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.9692. Min Act: -0.1700
Data Index: 2016246 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.9067. Min Act: -0.1700
Data Index: 7171907 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.8442. Min Act: -0.1700
Data Index: 3027689 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.7817. Min Act: -0.1700
Data Index: 5647496 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.7817. Min Act: -0.1700
Data Index: 8047346 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.7817. Min Act: -0.1700
Data Index: 6922328 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.7504. Min Act: -0.1700
Data Index: 7855441 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.7192. Min Act: -0.1700
Data Index: 8565146 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.7192. Min Act: -0.1700
Data Index: 6671063 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.6879. Min Act: -0.1700
Data Index: 4539761 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.6879. Min Act: -0.1700
Data Index: 4697838 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.6254. Min Act: -0.1700
Data Index: 8472648 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.6254. Min Act: -0.1700
Data Index: 51586 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.6567. Min Act: -0.1700
Data Index: 5873260 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.5942. Min Act: -0.1700
Data Index: 531147 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.5942. Min Act: -0.1700
Data Index: 6969498 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0317. Min Range: -5.0317
Max Act: 4.5942. Min Act: -0.1700
Data Index: 4399564 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19