Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0474. Min Range: -9.0474
Max Act: 9.0474. Min Act: -0.1700
Data Index: 5302184 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.7349. Min Act: -0.1700
Data Index: 1318957 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.7349. Min Act: -0.1700
Data Index: 4791443 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.6099. Min Act: -0.1700
Data Index: 1448433 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.6099. Min Act: -0.1700
Data Index: 888321 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.4849. Min Act: -0.1700
Data Index: 5213555 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.4849. Min Act: -0.1700
Data Index: 6584415 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.4224. Min Act: -0.1700
Data Index: 3490300 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.4224. Min Act: -0.1700
Data Index: 8249062 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.4224. Min Act: -0.1700
Data Index: 8297947 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.4224. Min Act: -0.1700
Data Index: 4434129 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.3599. Min Act: -0.1700
Data Index: 1637427 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.3599. Min Act: -0.1700
Data Index: 7009517 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.3599. Min Act: -0.1700
Data Index: 1840019 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.2974. Min Act: -0.1700
Data Index: 6154226 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.2974. Min Act: -0.1700
Data Index: 1580168 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.2974. Min Act: -0.1700
Data Index: 7295530 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.2974. Min Act: -0.1700
Data Index: 6869764 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.2349. Min Act: -0.1700
Data Index: 2960581 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0474. Min Range: -9.0474
Max Act: 8.1724. Min Act: -0.1700
Data Index: 7307107 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19