Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1159. Min Range: -9.1159
Max Act: 9.1159. Min Act: -0.1700
Data Index: 6350966 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1159. Min Range: -9.1159
Max Act: 9.0534. Min Act: -0.1700
Data Index: 6576525 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1159. Min Range: -9.1159
Max Act: 9.1159. Min Act: -0.1700
Data Index: 7697090 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.9909. Min Act: -0.1700
Data Index: 2718977 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.9284. Min Act: -0.1700
Data Index: 1862799 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.9284. Min Act: -0.1700
Data Index: 7816471 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.9284. Min Act: -0.1700
Data Index: 4582668 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.8659. Min Act: -0.1700
Data Index: 1211836 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.8659. Min Act: -0.1700
Data Index: 430235 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.8659. Min Act: -0.1700
Data Index: 7552572 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.8034. Min Act: -0.1700
Data Index: 8340374 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.8034. Min Act: -0.1700
Data Index: 6416416 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.8034. Min Act: -0.1682
Data Index: 3590408 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.8034. Min Act: -0.1700
Data Index: 8173963 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.6784. Min Act: -0.1700
Data Index: 3263444 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.6784. Min Act: -0.1700
Data Index: 2404483 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.7409. Min Act: -0.1700
Data Index: 2262823 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.7409. Min Act: -0.1699
Data Index: 4518169 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.7409. Min Act: -0.1696
Data Index: 7218373 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1159. Min Range: -9.1159
Max Act: 8.7409. Min Act: -0.1700
Data Index: 7038374 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19