Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.2863. Min Act: -0.1700
Data Index: 1332644 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.2534. Min Act: -0.1699
Data Index: 8590337 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.2203. Min Act: -0.1700
Data Index: 2329434 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.2368. Min Act: -0.1700
Data Index: 4085031 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.2037. Min Act: -0.1700
Data Index: 7747823 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1871. Min Act: -0.1700
Data Index: 7270392 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1871. Min Act: -0.1700
Data Index: 4948391 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1538. Min Act: -0.1700
Data Index: 673393 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1871. Min Act: -0.1700
Data Index: 3034549 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1705. Min Act: -0.1700
Data Index: 4921694 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1705. Min Act: -0.1700
Data Index: 4575871 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1538. Min Act: -0.1700
Data Index: 5423835 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1538. Min Act: -0.1700
Data Index: 3792683 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1371. Min Act: -0.1700
Data Index: 7568652 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1371. Min Act: -0.1700
Data Index: 1749088 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1204. Min Act: -0.1700
Data Index: 1317456 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1204. Min Act: -0.1700
Data Index: 6656757 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1204. Min Act: -0.1700
Data Index: 4189375 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1204. Min Act: -0.1700
Data Index: 3299701 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2863. Min Range: -2.2863
Max Act: 2.1204. Min Act: -0.1700
Data Index: 6712894 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19