Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.6722. Min Act: -0.1700
Data Index: 4603276 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.5472. Min Act: -0.1700
Data Index: 2252424 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.4222. Min Act: -0.1700
Data Index: 7523781 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.3597. Min Act: -0.1700
Data Index: 4094901 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.2972. Min Act: -0.1700
Data Index: 5575824 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.2972. Min Act: -0.1700
Data Index: 154602 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 1415381 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 1530931 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 5859722 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.1097. Min Act: -0.1700
Data Index: 5703535 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6722. Min Range: -8.6722
Max Act: 8.0472. Min Act: -0.1700
Data Index: 1257982 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.9847. Min Act: -0.1700
Data Index: 5576672 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.9847. Min Act: -0.1700
Data Index: 4605813 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.9847. Min Act: -0.1700
Data Index: 2143434 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.9847. Min Act: -0.1700
Data Index: 1368281 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.9847. Min Act: -0.1700
Data Index: 7734045 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.9222. Min Act: -0.1700
Data Index: 899289 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.9222. Min Act: -0.1700
Data Index: 8490707 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.9222. Min Act: -0.1700
Data Index: 5289158 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6722. Min Range: -8.6722
Max Act: 7.8597. Min Act: -0.1700
Data Index: 5208036 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19