Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5056 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.4428. Min Act: -0.1700
Data Index: 3966265 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.4428. Min Act: -0.1700
Data Index: 6142243 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.3178. Min Act: -0.1700
Data Index: 5809463 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.3178. Min Act: -0.1700
Data Index: 2991374 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.2865. Min Act: -0.1700
Data Index: 8220652 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.2553. Min Act: -0.1700
Data Index: 6215320 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.1928. Min Act: -0.1700
Data Index: 2273632 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.1303. Min Act: -0.1700
Data Index: 1844840 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.1615. Min Act: -0.1700
Data Index: 8410909 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.1615. Min Act: -0.1700
Data Index: 6919754 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.1303. Min Act: -0.1700
Data Index: 7998745 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.1303. Min Act: -0.1700
Data Index: 448233 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.1303. Min Act: -0.1700
Data Index: 4711860 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.0365. Min Act: -0.1700
Data Index: 6218852 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.0677. Min Act: -0.1700
Data Index: 3903372 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.0365. Min Act: -0.1700
Data Index: 4940832 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.0365. Min Act: -0.1700
Data Index: 7283760 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.0365. Min Act: -0.1700
Data Index: 6892592 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.0365. Min Act: -0.1700
Data Index: 4943209 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4428. Min Range: -4.4428
Max Act: 4.0365. Min Act: -0.1700
Data Index: 2164071 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19