Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5389 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.6786. Min Act: -0.1700
Data Index: 756994 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.6161. Min Act: -0.1700
Data Index: 7054689 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.3349. Min Act: -0.1700
Data Index: 7607687 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.1474. Min Act: -0.1700
Data Index: 6987957 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.1474. Min Act: -0.1700
Data Index: 4913264 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.1474. Min Act: -0.1700
Data Index: 649003 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.1161. Min Act: -0.1700
Data Index: 1376917 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.0849. Min Act: -0.1700
Data Index: 4049296 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.0849. Min Act: -0.1700
Data Index: 5387564 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.0536. Min Act: -0.1700
Data Index: 4033899 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.0224. Min Act: -0.1700
Data Index: 3322776 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6786. Min Range: -5.6786
Max Act: 5.0224. Min Act: -0.1700
Data Index: 5420362 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6786. Min Range: -5.6786
Max Act: 4.9911. Min Act: -0.1700
Data Index: 3534760 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6786. Min Range: -5.6786
Max Act: 4.9286. Min Act: -0.1700
Data Index: 1557686 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6786. Min Range: -5.6786
Max Act: 4.9599. Min Act: -0.1700
Data Index: 7329198 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6786. Min Range: -5.6786
Max Act: 4.9286. Min Act: -0.1700
Data Index: 5428294 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6786. Min Range: -5.6786
Max Act: 4.9286. Min Act: -0.1700
Data Index: 4049297 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6786. Min Range: -5.6786
Max Act: 4.9286. Min Act: -0.1700
Data Index: 6533344 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6786. Min Range: -5.6786
Max Act: 4.9599. Min Act: -0.1700
Data Index: 4802129 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6786. Min Range: -5.6786
Max Act: 4.8661. Min Act: -0.1700
Data Index: 4663054 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19