Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 629 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.9605. Min Act: -0.1700
Data Index: 5815915 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.7105. Min Act: -0.1700
Data Index: 5099508 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.3355. Min Act: -0.1700
Data Index: 6163188 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.1480. Min Act: -0.1700
Data Index: 7862346 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.2105. Min Act: -0.1700
Data Index: 7145024 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.2105. Min Act: -0.1700
Data Index: 1136173 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.1480. Min Act: -0.1700
Data Index: 1881403 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.1480. Min Act: -0.1700
Data Index: 1878541 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.0855. Min Act: -0.1700
Data Index: 5710950 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.0855. Min Act: -0.1700
Data Index: 5294643 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.0230. Min Act: -0.1700
Data Index: 2260837 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9605. Min Range: -8.9605
Max Act: 7.9605. Min Act: -0.1700
Data Index: 4642770 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.0230. Min Act: -0.1700
Data Index: 694344 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.0230. Min Act: -0.1700
Data Index: 5123416 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9605. Min Range: -8.9605
Max Act: 7.9293. Min Act: -0.1700
Data Index: 4036171 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9605. Min Range: -8.9605
Max Act: 8.0230. Min Act: -0.1700
Data Index: 2559906 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9605. Min Range: -8.9605
Max Act: 7.9605. Min Act: -0.1700
Data Index: 1997169 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9605. Min Range: -8.9605
Max Act: 7.9293. Min Act: -0.1700
Data Index: 752393 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9605. Min Range: -8.9605
Max Act: 7.9293. Min Act: -0.1700
Data Index: 5381450 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9605. Min Range: -8.9605
Max Act: 7.9293. Min Act: -0.1700
Data Index: 3883542 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19