Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1507 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.4635. Min Act: -0.1700
Data Index: 76622 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.3165. Min Act: -0.1700
Data Index: 62382 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.3165. Min Act: -0.1700
Data Index: 2251604 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.2671. Min Act: -0.1700
Data Index: 6979367 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.2506. Min Act: -0.1700
Data Index: 4592342 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.2671. Min Act: -0.1700
Data Index: 7511528 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.2671. Min Act: -0.1700
Data Index: 7447576 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.2671. Min Act: -0.1700
Data Index: 1353456 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.2009. Min Act: -0.1700
Data Index: 5258873 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.2009. Min Act: -0.1700
Data Index: 5017626 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1677. Min Act: -0.1700
Data Index: 2504457 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1843. Min Act: -0.1700
Data Index: 7725239 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1677. Min Act: -0.1700
Data Index: 3480019 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1677. Min Act: -0.1700
Data Index: 3623209 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1176. Min Act: -0.1700
Data Index: 4160160 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1510. Min Act: -0.1700
Data Index: 1396781 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1510. Min Act: -0.1700
Data Index: 5440065 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1343. Min Act: -0.1700
Data Index: 1589436 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1343. Min Act: -0.1700
Data Index: 2238220 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4635. Min Range: -2.4635
Max Act: 2.1343. Min Act: -0.1700
Data Index: 4160158 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19