Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.4420. Min Act: -0.1700
Data Index: 7457006 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.2545. Min Act: -0.1700
Data Index: 2187979 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.1608. Min Act: -0.1700
Data Index: 925442 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.1920. Min Act: -0.1700
Data Index: 5607631 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.1608. Min Act: -0.1700
Data Index: 384562 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.1295. Min Act: -0.1700
Data Index: 6268108 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.0358. Min Act: -0.1700
Data Index: 8414779 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.0358. Min Act: -0.1700
Data Index: 6458017 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.0670. Min Act: -0.1700
Data Index: 6523290 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.0358. Min Act: -0.1700
Data Index: 8756362 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.0045. Min Act: -0.1700
Data Index: 6614878 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.0045. Min Act: -0.1700
Data Index: 5431719 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4420. Min Range: -6.4420
Max Act: 5.9733. Min Act: -0.1700
Data Index: 721804 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4420. Min Range: -6.4420
Max Act: 5.9733. Min Act: -0.1700
Data Index: 4203748 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.0045. Min Act: -0.1700
Data Index: 1467903 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.0045. Min Act: -0.1700
Data Index: 7969183 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4420. Min Range: -6.4420
Max Act: 6.0045. Min Act: -0.1700
Data Index: 3850390 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4420. Min Range: -6.4420
Max Act: 5.9733. Min Act: -0.1700
Data Index: 2221439 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4420. Min Range: -6.4420
Max Act: 5.9733. Min Act: -0.1700
Data Index: 4114000 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4420. Min Range: -6.4420
Max Act: 5.9420. Min Act: -0.1700
Data Index: 3270645 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19