Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.8515. Min Act: -0.1700
Data Index: 4357740 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.8346. Min Act: -0.1693
Data Index: 95399 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.8346. Min Act: -0.1688
Data Index: 7537441 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7842. Min Act: -0.1700
Data Index: 5468312 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7675. Min Act: -0.1700
Data Index: 3104910 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7675. Min Act: -0.1700
Data Index: 6562434 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7509. Min Act: -0.1675
Data Index: 7298993 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7509. Min Act: -0.1690
Data Index: 4357741 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7509. Min Act: -0.1700
Data Index: 2978734 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7509. Min Act: -0.1700
Data Index: 1507258 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7344. Min Act: -0.1700
Data Index: 6693066 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7509. Min Act: -0.1693
Data Index: 434838 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7180. Min Act: -0.1700
Data Index: 364915 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7344. Min Act: -0.1691
Data Index: 1507256 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7344. Min Act: -0.1699
Data Index: 2588271 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7016. Min Act: -0.1696
Data Index: 2588272 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7180. Min Act: -0.1700
Data Index: 5639181 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7180. Min Act: -0.1700
Data Index: 5571144 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7180. Min Act: -0.1700
Data Index: 5457482 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8515. Min Range: -0.8515
Max Act: 0.7180. Min Act: -0.1700
Data Index: 3401613 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19