Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.9253. Min Act: -0.1700
Data Index: 5842038 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8471. Min Act: -0.1700
Data Index: 7889857 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.7845. Min Act: -0.1700
Data Index: 2342646 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.7845. Min Act: -0.1700
Data Index: 1952741 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.7689. Min Act: -0.1700
Data Index: 1978826 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.7689. Min Act: -0.1700
Data Index: 7152513 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.7220. Min Act: -0.1700
Data Index: 1554505 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6751. Min Act: -0.1700
Data Index: 2107751 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6751. Min Act: -0.1700
Data Index: 6168356 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6751. Min Act: -0.1700
Data Index: 5101228 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6751. Min Act: -0.1700
Data Index: 4581529 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6594. Min Act: -0.1700
Data Index: 4492040 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6281. Min Act: -0.1700
Data Index: 5801383 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6125. Min Act: -0.1700
Data Index: 4707723 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6125. Min Act: -0.1700
Data Index: 3554467 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6125. Min Act: -0.1700
Data Index: 1232167 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6125. Min Act: -0.1700
Data Index: 8284993 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.5968. Min Act: -0.1700
Data Index: 2880735 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.6125. Min Act: -0.1700
Data Index: 8574887 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.5812. Min Act: -0.1700
Data Index: 4601402 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19