Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3979 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.9272. Min Act: -0.1700
Data Index: 5203502 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.8647. Min Act: -0.1700
Data Index: 4347807 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7085. Min Act: -0.1700
Data Index: 8340771 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.6772. Min Act: -0.1700
Data Index: 1982340 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.5522. Min Act: -0.1700
Data Index: 1155219 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.4897. Min Act: -0.1700
Data Index: 2723130 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.4897. Min Act: -0.1700
Data Index: 2723129 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.4897. Min Act: -0.1700
Data Index: 3047499 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.4585. Min Act: -0.1700
Data Index: 3568812 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.4272. Min Act: -0.1700
Data Index: 4038414 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.4272. Min Act: -0.1700
Data Index: 4507934 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.4272. Min Act: -0.1700
Data Index: 4063504 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.4272. Min Act: -0.1700
Data Index: 2387717 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.4272. Min Act: -0.1700
Data Index: 4465824 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.3960. Min Act: -0.1700
Data Index: 5700780 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.3960. Min Act: -0.1700
Data Index: 5072521 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.3647. Min Act: -0.1700
Data Index: 3879881 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.3647. Min Act: -0.1700
Data Index: 606938 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.3335. Min Act: -0.1700
Data Index: 4025786 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.3335. Min Act: -0.1700
Data Index: 3735911 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19