Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2696 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.9042. Min Act: -0.1700
Data Index: 7638163 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.7792. Min Act: -0.1700
Data Index: 6964397 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.6542. Min Act: -0.1700
Data Index: 808176 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.5605. Min Act: -0.1700
Data Index: 8770996 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.6230. Min Act: -0.1700
Data Index: 4396280 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.6542. Min Act: -0.1700
Data Index: 1581487 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.5605. Min Act: -0.1700
Data Index: 477274 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.5605. Min Act: -0.1700
Data Index: 2085809 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.5292. Min Act: -0.1700
Data Index: 2665127 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.5292. Min Act: -0.1700
Data Index: 1333395 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.5292. Min Act: -0.1700
Data Index: 4959765 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.4980. Min Act: -0.1700
Data Index: 7345994 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.4667. Min Act: -0.1700
Data Index: 6551321 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.4355. Min Act: -0.1700
Data Index: 3348019 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.4355. Min Act: -0.1700
Data Index: 1561333 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.4355. Min Act: -0.1700
Data Index: 8350189 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.4042. Min Act: -0.1700
Data Index: 2490055 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.4042. Min Act: -0.1700
Data Index: 7245281 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.3730. Min Act: -0.1700
Data Index: 8468524 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9042. Min Range: -6.9042
Max Act: 6.3730. Min Act: -0.1700
Data Index: 4874255 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19