Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5707 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1266. Min Range: -6.1266
Max Act: 6.1266. Min Act: -0.1700
Data Index: 2393107 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1266. Min Range: -6.1266
Max Act: 6.0953. Min Act: -0.1700
Data Index: 7296552 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1266. Min Range: -6.1266
Max Act: 6.0641. Min Act: -0.1700
Data Index: 405589 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.9078. Min Act: -0.1700
Data Index: 2770823 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.8453. Min Act: -0.1700
Data Index: 792967 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.8141. Min Act: -0.1700
Data Index: 1474350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.7516. Min Act: -0.1700
Data Index: 11495 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.7203. Min Act: -0.1700
Data Index: 8429959 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.6266. Min Act: -0.1700
Data Index: 5736871 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.5953. Min Act: -0.1700
Data Index: 4514039 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.5953. Min Act: -0.1700
Data Index: 5809112 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.5953. Min Act: -0.1700
Data Index: 6576984 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.5328. Min Act: -0.1700
Data Index: 306850 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.4703. Min Act: -0.1700
Data Index: 7580644 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.4703. Min Act: -0.1700
Data Index: 6613330 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.4391. Min Act: -0.1700
Data Index: 5042969 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.4391. Min Act: -0.1700
Data Index: 8775718 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.4078. Min Act: -0.1700
Data Index: 147009 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.4078. Min Act: -0.1700
Data Index: 4361107 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1266. Min Range: -6.1266
Max Act: 5.4078. Min Act: -0.1700
Data Index: 3838682 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19