Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1020 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3523. Min Range: -6.3523
Max Act: 6.3523. Min Act: -0.1700
Data Index: 6237634 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3523. Min Range: -6.3523
Max Act: 6.2273. Min Act: -0.1700
Data Index: 5434928 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3523. Min Range: -6.3523
Max Act: 6.1648. Min Act: -0.1700
Data Index: 169204 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3523. Min Range: -6.3523
Max Act: 6.1023. Min Act: -0.1700
Data Index: 1499511 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3523. Min Range: -6.3523
Max Act: 6.0086. Min Act: -0.1700
Data Index: 1954744 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9773. Min Act: -0.1700
Data Index: 2730414 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9773. Min Act: -0.1700
Data Index: 1334842 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9773. Min Act: -0.1700
Data Index: 2152760 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9773. Min Act: -0.1700
Data Index: 7863480 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9461. Min Act: -0.1700
Data Index: 3586680 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9773. Min Act: -0.1700
Data Index: 89247 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9461. Min Act: -0.1700
Data Index: 5197230 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9148. Min Act: -0.1700
Data Index: 3943278 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9148. Min Act: -0.1700
Data Index: 8803410 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.9148. Min Act: -0.1700
Data Index: 7841161 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.8836. Min Act: -0.1700
Data Index: 4358940 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.8836. Min Act: -0.1700
Data Index: 8796498 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.8836. Min Act: -0.1700
Data Index: 3219970 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.8523. Min Act: -0.1700
Data Index: 4206869 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3523. Min Range: -6.3523
Max Act: 5.8523. Min Act: -0.1700
Data Index: 4029130 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19