Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0703. Min Range: -7.0703
Max Act: 7.0703. Min Act: -0.1700
Data Index: 431587 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.9765. Min Act: -0.1700
Data Index: 3961870 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.8828. Min Act: -0.1700
Data Index: 4074908 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.7890. Min Act: -0.1700
Data Index: 235180 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.7890. Min Act: -0.1700
Data Index: 5762221 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.7578. Min Act: -0.1700
Data Index: 1051856 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.7265. Min Act: -0.1700
Data Index: 6994348 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.6953. Min Act: -0.1700
Data Index: 7130891 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.6953. Min Act: -0.1700
Data Index: 65219 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.7265. Min Act: -0.1700
Data Index: 8016800 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.6953. Min Act: -0.1700
Data Index: 2474604 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.6015. Min Act: -0.1700
Data Index: 8355274 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.6015. Min Act: -0.1700
Data Index: 409043 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.5703. Min Act: -0.1700
Data Index: 3909800 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.5390. Min Act: -0.1700
Data Index: 8547640 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.5078. Min Act: -0.1700
Data Index: 4649331 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.4765. Min Act: -0.1700
Data Index: 6810518 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.4765. Min Act: -0.1700
Data Index: 404404 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.4765. Min Act: -0.1700
Data Index: 3665097 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0703. Min Range: -7.0703
Max Act: 6.4453. Min Act: -0.1700
Data Index: 1053982 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19