Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2156 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.1659. Min Act: -0.1700
Data Index: 8587499 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.1659. Min Act: -0.1700
Data Index: 3690639 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.1502. Min Act: -0.1700
Data Index: 5227093 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.1344. Min Act: -0.1700
Data Index: 5887120 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.1187. Min Act: -0.1700
Data Index: 6238508 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.1187. Min Act: -0.1700
Data Index: 3170560 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.1029. Min Act: -0.1700
Data Index: 144078 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.1029. Min Act: -0.1700
Data Index: 1171512 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0714. Min Act: -0.1700
Data Index: 5982275 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0556. Min Act: -0.1700
Data Index: 3774503 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0556. Min Act: -0.1700
Data Index: 1515970 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0556. Min Act: -0.1700
Data Index: 7875719 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0556. Min Act: -0.1700
Data Index: 1989925 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0240. Min Act: -0.1700
Data Index: 635902 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0240. Min Act: -0.1700
Data Index: 7564235 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0240. Min Act: -0.1700
Data Index: 78201 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0240. Min Act: -0.1700
Data Index: 4973855 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0240. Min Act: -0.1700
Data Index: 3869790 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0240. Min Act: -0.1700
Data Index: 7052786 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1659. Min Range: -3.1659
Max Act: 3.0240. Min Act: -0.1700
Data Index: 3004203 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19