Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1352 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0536. Min Range: -5.0536
Max Act: 5.0536. Min Act: -0.1700
Data Index: 7769688 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0536. Min Range: -5.0536
Max Act: 5.0536. Min Act: -0.1700
Data Index: 2911271 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.9911. Min Act: -0.1700
Data Index: 5947752 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0536. Min Range: -5.0536
Max Act: 5.0224. Min Act: -0.1700
Data Index: 8348157 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0536. Min Range: -5.0536
Max Act: 5.0224. Min Act: -0.1700
Data Index: 594052 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.9911. Min Act: -0.1700
Data Index: 5029930 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.9599. Min Act: -0.1700
Data Index: 4238170 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.9286. Min Act: -0.1700
Data Index: 2383801 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.9286. Min Act: -0.1700
Data Index: 5430195 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.8974. Min Act: -0.1700
Data Index: 3781648 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.8974. Min Act: -0.1700
Data Index: 8118626 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.8974. Min Act: -0.1700
Data Index: 6169836 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.8349. Min Act: -0.1700
Data Index: 8082407 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.8349. Min Act: -0.1700
Data Index: 4188893 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.8036. Min Act: -0.1700
Data Index: 8745425 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.8036. Min Act: -0.1700
Data Index: 658305 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.7724. Min Act: -0.1700
Data Index: 2853601 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.7724. Min Act: -0.1700
Data Index: 6096489 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.7411. Min Act: -0.1700
Data Index: 2983796 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0536. Min Range: -5.0536
Max Act: 4.7411. Min Act: -0.1700
Data Index: 3725487 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19