Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.5627. Min Act: -0.1700
Data Index: 5211779 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.3127. Min Act: -0.1700
Data Index: 7029792 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.2815. Min Act: -0.1700
Data Index: 5234748 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.2815. Min Act: -0.1700
Data Index: 585965 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.2190. Min Act: -0.1700
Data Index: 2139808 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.1877. Min Act: -0.1700
Data Index: 921809 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.1565. Min Act: -0.1700
Data Index: 4616141 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.1877. Min Act: -0.1700
Data Index: 5034252 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.1877. Min Act: -0.1700
Data Index: 6813731 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.1565. Min Act: -0.1700
Data Index: 463030 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.1252. Min Act: -0.1700
Data Index: 6939561 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.1252. Min Act: -0.1700
Data Index: 4287344 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.1252. Min Act: -0.1700
Data Index: 2359413 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.1252. Min Act: -0.1700
Data Index: 1256432 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.0940. Min Act: -0.1700
Data Index: 3668732 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.0940. Min Act: -0.1700
Data Index: 2615540 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.0940. Min Act: -0.1700
Data Index: 2187222 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.0940. Min Act: -0.1700
Data Index: 5183268 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.0940. Min Act: -0.1700
Data Index: 3824233 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5627. Min Range: -5.5627
Max Act: 5.0940. Min Act: -0.1700
Data Index: 1347920 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19