Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1207. Min Range: -3.1207
Max Act: 3.1207. Min Act: -0.1700
Data Index: 4995160 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1207. Min Range: -3.1207
Max Act: 3.1207. Min Act: -0.1700
Data Index: 657406 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1207. Min Range: -3.1207
Max Act: 3.1049. Min Act: -0.1700
Data Index: 2571588 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1207. Min Range: -3.1207
Max Act: 3.0260. Min Act: -0.1700
Data Index: 2302175 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1207. Min Range: -3.1207
Max Act: 3.0260. Min Act: -0.1700
Data Index: 4064821 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9944. Min Act: -0.1700
Data Index: 5537624 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9944. Min Act: -0.1700
Data Index: 5152523 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9944. Min Act: -0.1700
Data Index: 59613 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9944. Min Act: -0.1700
Data Index: 2475017 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9944. Min Act: -0.1700
Data Index: 8195631 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9628. Min Act: -0.1700
Data Index: 4306835 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9628. Min Act: -0.1700
Data Index: 7876906 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9628. Min Act: -0.1700
Data Index: 4489235 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9470. Min Act: -0.1700
Data Index: 710827 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9470. Min Act: -0.1700
Data Index: 3844514 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9628. Min Act: -0.1700
Data Index: 860663 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9470. Min Act: -0.1700
Data Index: 538985 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9153. Min Act: -0.1700
Data Index: 2176672 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9312. Min Act: -0.1700
Data Index: 1720632 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1207. Min Range: -3.1207
Max Act: 2.9312. Min Act: -0.1700
Data Index: 2202731 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19