Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.8115. Min Act: -0.1700
Data Index: 2882637 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.7490. Min Act: -0.1700
Data Index: 2782341 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.7803. Min Act: -0.1700
Data Index: 8622122 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.7490. Min Act: -0.1700
Data Index: 2502636 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.7178. Min Act: -0.1700
Data Index: 304895 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6865. Min Act: -0.1700
Data Index: 4835917 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6865. Min Act: -0.1700
Data Index: 3942437 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6865. Min Act: -0.1700
Data Index: 263697 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6553. Min Act: -0.1700
Data Index: 1355413 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6553. Min Act: -0.1700
Data Index: 1223533 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6553. Min Act: -0.1700
Data Index: 1834542 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6553. Min Act: -0.1700
Data Index: 1183468 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6865. Min Act: -0.1700
Data Index: 3272405 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6553. Min Act: -0.1700
Data Index: 7560694 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6553. Min Act: -0.1700
Data Index: 7243603 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6240. Min Act: -0.1700
Data Index: 6222438 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6240. Min Act: -0.1700
Data Index: 2526621 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6240. Min Act: -0.1700
Data Index: 421382 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.5928. Min Act: -0.1700
Data Index: 7022333 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8115. Min Range: -4.8115
Max Act: 4.6240. Min Act: -0.1700
Data Index: 7071627 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19