Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.5328. Min Act: -0.1700
Data Index: 8809199 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.4703. Min Act: -0.1700
Data Index: 5086486 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.4390. Min Act: -0.1700
Data Index: 8539052 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.3765. Min Act: -0.1700
Data Index: 3708792 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.3140. Min Act: -0.1700
Data Index: 2712879 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.3453. Min Act: -0.1700
Data Index: 183624 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.2828. Min Act: -0.1700
Data Index: 1335320 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.3140. Min Act: -0.1700
Data Index: 8767889 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.3140. Min Act: -0.1700
Data Index: 2562601 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.2515. Min Act: -0.1700
Data Index: 5268972 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.2515. Min Act: -0.1700
Data Index: 1948854 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.2203. Min Act: -0.1700
Data Index: 8294862 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.2203. Min Act: -0.1700
Data Index: 4428208 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.2515. Min Act: -0.1700
Data Index: 4614523 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.2203. Min Act: -0.1700
Data Index: 7036880 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.1890. Min Act: -0.1700
Data Index: 7821974 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.1578. Min Act: -0.1700
Data Index: 1744552 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.1890. Min Act: -0.1700
Data Index: 4539647 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.1578. Min Act: -0.1700
Data Index: 7835423 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5328. Min Range: -6.5328
Max Act: 6.1578. Min Act: -0.1700
Data Index: 5431772 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19