Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2242 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.5207. Min Act: -0.1700
Data Index: 3873989 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.4270. Min Act: -0.1700
Data Index: 6320101 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.3645. Min Act: -0.1700
Data Index: 226016 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.3020. Min Act: -0.1700
Data Index: 1191387 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.2395. Min Act: -0.1700
Data Index: 8695534 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.2395. Min Act: -0.1700
Data Index: 7116494 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.2082. Min Act: -0.1700
Data Index: 4239100 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.1770. Min Act: -0.1700
Data Index: 1126908 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.1145. Min Act: -0.1700
Data Index: 6669331 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.0832. Min Act: -0.1700
Data Index: 790283 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.0832. Min Act: -0.1700
Data Index: 1596872 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.0520. Min Act: -0.1700
Data Index: 1452768 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.0207. Min Act: -0.1700
Data Index: 1490013 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.0207. Min Act: -0.1700
Data Index: 2972619 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5207. Min Range: -7.5207
Max Act: 6.9895. Min Act: -0.1700
Data Index: 5170292 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5207. Min Range: -7.5207
Max Act: 7.0207. Min Act: -0.1700
Data Index: 3600867 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5207. Min Range: -7.5207
Max Act: 6.9895. Min Act: -0.1700
Data Index: 676191 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5207. Min Range: -7.5207
Max Act: 6.9895. Min Act: -0.1700
Data Index: 6716006 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5207. Min Range: -7.5207
Max Act: 6.9582. Min Act: -0.1700
Data Index: 1205968 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5207. Min Range: -7.5207
Max Act: 6.9582. Min Act: -0.1700
Data Index: 4682200 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19