Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6342 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.9602. Min Act: -0.1700
Data Index: 437377 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.9001. Min Act: -0.1692
Data Index: 4423710 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.8745. Min Act: -0.1697
Data Index: 4826929 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.8660. Min Act: -0.1699
Data Index: 3887781 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.8490. Min Act: -0.1693
Data Index: 4776590 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.8405. Min Act: -0.1698
Data Index: 6330031 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.8321. Min Act: -0.1697
Data Index: 2773662 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.8236. Min Act: -0.1700
Data Index: 8623244 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.8236. Min Act: -0.1599
Data Index: 2516186 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.8068. Min Act: -0.1700
Data Index: 148604 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7984. Min Act: -0.1700
Data Index: 3156613 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7817. Min Act: -0.1698
Data Index: 1751689 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7817. Min Act: -0.1689
Data Index: 5473780 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7733. Min Act: -0.1697
Data Index: 6513871 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7567. Min Act: -0.1678
Data Index: 845250 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7650. Min Act: -0.1700
Data Index: 137430 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7650. Min Act: -0.1700
Data Index: 5227825 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7733. Min Act: -0.1651
Data Index: 4914493 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7567. Min Act: -0.1659
Data Index: 7977438 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9602. Min Range: -0.9602
Max Act: 0.7484. Min Act: -0.1700
Data Index: 4401192 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19