Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2932 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.6977. Min Act: -0.1700
Data Index: 6110637 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.6332. Min Act: -0.1700
Data Index: 249202 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.6332. Min Act: -0.1698
Data Index: 8687072 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.6332. Min Act: -0.1700
Data Index: 2214788 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.6094. Min Act: -0.1700
Data Index: 975230 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.6094. Min Act: -0.1700
Data Index: 1410108 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.6015. Min Act: -0.1700
Data Index: 3640558 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.6015. Min Act: -0.1699
Data Index: 1754633 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5858. Min Act: -0.1698
Data Index: 2045661 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5936. Min Act: -0.1700
Data Index: 1417323 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5858. Min Act: -0.1700
Data Index: 2419789 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5780. Min Act: -0.1700
Data Index: 5395122 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5780. Min Act: -0.1700
Data Index: 5401986 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5702. Min Act: -0.1700
Data Index: 3761098 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5702. Min Act: -0.1700
Data Index: 6378913 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5624. Min Act: -0.1699
Data Index: 3707337 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5624. Min Act: -0.1676
Data Index: 974552 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5547. Min Act: -0.1686
Data Index: 2770094 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5470. Min Act: -0.1699
Data Index: 8535830 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6977. Min Range: -0.6977
Max Act: 0.5547. Min Act: -0.1700
Data Index: 578430 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19