Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1742 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0864. Min Range: -5.0864
Max Act: 5.0552. Min Act: -0.1700
Data Index: 4412058 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0864. Min Range: -5.0864
Max Act: 5.0864. Min Act: -0.1700
Data Index: 1295362 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0864. Min Range: -5.0864
Max Act: 5.0552. Min Act: -0.1700
Data Index: 1578059 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0864. Min Range: -5.0864
Max Act: 5.0239. Min Act: -0.1700
Data Index: 5929682 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9927. Min Act: -0.1700
Data Index: 4522304 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9927. Min Act: -0.1700
Data Index: 4500679 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9927. Min Act: -0.1700
Data Index: 7055966 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9927. Min Act: -0.1700
Data Index: 8584629 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9927. Min Act: -0.1700
Data Index: 4526399 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9927. Min Act: -0.1700
Data Index: 5877928 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9614. Min Act: -0.1700
Data Index: 3766608 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9614. Min Act: -0.1700
Data Index: 8503338 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9302. Min Act: -0.1700
Data Index: 2772418 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9614. Min Act: -0.1700
Data Index: 1683867 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9302. Min Act: -0.1700
Data Index: 4374127 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9302. Min Act: -0.1700
Data Index: 3128334 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9302. Min Act: -0.1700
Data Index: 5183614 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.9302. Min Act: -0.1700
Data Index: 5379869 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.8989. Min Act: -0.1700
Data Index: 5087290 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0864. Min Range: -5.0864
Max Act: 4.8677. Min Act: -0.1700
Data Index: 1333213 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19