Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.3247. Min Act: -0.1700
Data Index: 746306 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.2622. Min Act: -0.1700
Data Index: 7677291 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.2309. Min Act: -0.1700
Data Index: 3603151 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.1997. Min Act: -0.1700
Data Index: 5772631 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.1059. Min Act: -0.1700
Data Index: 4247472 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.0747. Min Act: -0.1700
Data Index: 6959170 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.9809. Min Act: -0.1700
Data Index: 131476 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.9184. Min Act: -0.1700
Data Index: 746309 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.9184. Min Act: -0.1700
Data Index: 164539 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.9184. Min Act: -0.1700
Data Index: 4483559 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.9184. Min Act: -0.1700
Data Index: 8072694 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.8247. Min Act: -0.1700
Data Index: 291885 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.8247. Min Act: -0.1700
Data Index: 5488577 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.8247. Min Act: -0.1700
Data Index: 6216852 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7934. Min Act: -0.1700
Data Index: 1635776 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7622. Min Act: -0.1700
Data Index: 5699171 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7309. Min Act: -0.1700
Data Index: 6638840 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7622. Min Act: -0.1700
Data Index: 2291056 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7309. Min Act: -0.1700
Data Index: 783424 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7309. Min Act: -0.1700
Data Index: 5622425 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19