Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.5090. Min Act: -0.1700
Data Index: 691103 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.3840. Min Act: -0.1700
Data Index: 3897645 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.3215. Min Act: -0.1700
Data Index: 3519047 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.2590. Min Act: -0.1700
Data Index: 3332928 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.2590. Min Act: -0.1700
Data Index: 6660729 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.2903. Min Act: -0.1700
Data Index: 73169 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.2903. Min Act: -0.1700
Data Index: 2125508 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.2278. Min Act: -0.1700
Data Index: 5837001 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.1965. Min Act: -0.1700
Data Index: 1815788 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.1653. Min Act: -0.1700
Data Index: 5600399 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.1653. Min Act: -0.1700
Data Index: 3370578 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.1028. Min Act: -0.1700
Data Index: 6921063 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.1340. Min Act: -0.1700
Data Index: 7367681 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.1028. Min Act: -0.1700
Data Index: 5970686 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.1028. Min Act: -0.1700
Data Index: 5447958 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.0715. Min Act: -0.1700
Data Index: 761150 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.0403. Min Act: -0.1700
Data Index: 664894 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.0090. Min Act: -0.1700
Data Index: 1637805 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5090. Min Range: -7.5090
Max Act: 7.0090. Min Act: -0.1700
Data Index: 7574361 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5090. Min Range: -7.5090
Max Act: 6.9465. Min Act: -0.1700
Data Index: 997284 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19