Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4051. Min Range: -10.4051
Max Act: 10.4051. Min Act: -0.1700
Data Index: 648336 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4051. Min Range: -10.4051
Max Act: 10.4051. Min Act: -0.1700
Data Index: 6407427 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4051. Min Range: -10.4051
Max Act: 10.2176. Min Act: -0.1700
Data Index: 5213925 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4051. Min Range: -10.4051
Max Act: 10.1551. Min Act: -0.1700
Data Index: 7607850 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4051. Min Range: -10.4051
Max Act: 10.1551. Min Act: -0.1700
Data Index: 7592808 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4051. Min Range: -10.4051
Max Act: 10.1551. Min Act: -0.1700
Data Index: 7337193 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4051. Min Range: -10.4051
Max Act: 10.0926. Min Act: -0.1700
Data Index: 4927737 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4051. Min Range: -10.4051
Max Act: 10.0926. Min Act: -0.1700
Data Index: 5938464 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4051. Min Range: -10.4051
Max Act: 10.0926. Min Act: -0.1700
Data Index: 2873428 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.9051. Min Act: -0.1700
Data Index: 2278566 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.9676. Min Act: -0.1700
Data Index: 61344 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.9676. Min Act: -0.1700
Data Index: 7986873 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.9051. Min Act: -0.1700
Data Index: 6830338 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.9051. Min Act: -0.1700
Data Index: 952179 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.9051. Min Act: -0.1700
Data Index: 8532073 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.8426. Min Act: -0.1700
Data Index: 1306788 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.8426. Min Act: -0.1700
Data Index: 4222415 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.7801. Min Act: -0.1700
Data Index: 1785652 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.7801. Min Act: -0.1700
Data Index: 5204181 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4051. Min Range: -10.4051
Max Act: 9.7801. Min Act: -0.1700
Data Index: 4281703 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19