Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1827. Min Range: -7.1827
Max Act: 7.1827. Min Act: -0.1700
Data Index: 8444991 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1827. Min Range: -7.1827
Max Act: 7.1202. Min Act: -0.1700
Data Index: 3129578 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1827. Min Range: -7.1827
Max Act: 7.0890. Min Act: -0.1700
Data Index: 7650171 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.9952. Min Act: -0.1700
Data Index: 1875544 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.9640. Min Act: -0.1700
Data Index: 2077548 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.9640. Min Act: -0.1700
Data Index: 1889735 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.9327. Min Act: -0.1700
Data Index: 408326 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.9015. Min Act: -0.1700
Data Index: 6137574 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.8702. Min Act: -0.1700
Data Index: 3468560 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.8702. Min Act: -0.1700
Data Index: 63226 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.8702. Min Act: -0.1700
Data Index: 2345829 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.7765. Min Act: -0.1700
Data Index: 1817146 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.7765. Min Act: -0.1700
Data Index: 2395387 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.8077. Min Act: -0.1700
Data Index: 2498151 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.8390. Min Act: -0.1700
Data Index: 7067114 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.8077. Min Act: -0.1700
Data Index: 6934096 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.7765. Min Act: -0.1700
Data Index: 6741128 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.7452. Min Act: -0.1700
Data Index: 5930483 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.7452. Min Act: -0.1700
Data Index: 4443356 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1827. Min Range: -7.1827
Max Act: 6.7452. Min Act: -0.1700
Data Index: 5826383 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19