Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 983 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.4488. Min Act: -0.1700
Data Index: 938214 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.4488. Min Act: -0.1700
Data Index: 7009010 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.3863. Min Act: -0.1700
Data Index: 3402453 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.1676. Min Act: -0.1700
Data Index: 8033280 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.1988. Min Act: -0.1700
Data Index: 8419717 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.1363. Min Act: -0.1700
Data Index: 8005284 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.1051. Min Act: -0.1700
Data Index: 7639748 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.0426. Min Act: -0.1700
Data Index: 1203639 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.0426. Min Act: -0.1700
Data Index: 2634267 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.0113. Min Act: -0.1700
Data Index: 4336285 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4488. Min Range: -6.4488
Max Act: 6.0113. Min Act: -0.1700
Data Index: 3196716 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4488. Min Range: -6.4488
Max Act: 5.9801. Min Act: -0.1700
Data Index: 3504662 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4488. Min Range: -6.4488
Max Act: 5.9801. Min Act: -0.1700
Data Index: 8631813 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4488. Min Range: -6.4488
Max Act: 5.9801. Min Act: -0.1700
Data Index: 391008 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4488. Min Range: -6.4488
Max Act: 5.9801. Min Act: -0.1700
Data Index: 4013420 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4488. Min Range: -6.4488
Max Act: 5.9488. Min Act: -0.1700
Data Index: 4458901 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4488. Min Range: -6.4488
Max Act: 5.9488. Min Act: -0.1700
Data Index: 8438392 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4488. Min Range: -6.4488
Max Act: 5.9176. Min Act: -0.1700
Data Index: 5845257 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4488. Min Range: -6.4488
Max Act: 5.9176. Min Act: -0.1700
Data Index: 8055242 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4488. Min Range: -6.4488
Max Act: 5.9176. Min Act: -0.1700
Data Index: 1530327 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19