Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3401 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.6936. Min Act: -0.1700
Data Index: 5661067 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.6623. Min Act: -0.1700
Data Index: 3936958 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.6310. Min Act: -0.1700
Data Index: 6695369 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.6310. Min Act: -0.1700
Data Index: 149329 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.5997. Min Act: -0.1700
Data Index: 3194337 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.5840. Min Act: -0.1700
Data Index: 8400925 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.5371. Min Act: -0.1700
Data Index: 2214745 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.5527. Min Act: -0.1700
Data Index: 8449688 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.5214. Min Act: -0.1700
Data Index: 1830570 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.5371. Min Act: -0.1700
Data Index: 2252779 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.4901. Min Act: -0.1700
Data Index: 1601232 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.4744. Min Act: -0.1700
Data Index: 3774133 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.4901. Min Act: -0.1700
Data Index: 6759750 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.5057. Min Act: -0.1700
Data Index: 1212654 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.4744. Min Act: -0.1700
Data Index: 4126625 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.4901. Min Act: -0.1700
Data Index: 1596913 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.4744. Min Act: -0.1700
Data Index: 6536319 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.4744. Min Act: -0.1700
Data Index: 5754091 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.4587. Min Act: -0.1700
Data Index: 627728 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6936. Min Range: -3.6936
Max Act: 3.4587. Min Act: -0.1700
Data Index: 2633664 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19