Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1526. Min Range: -4.1526
Max Act: 4.1526. Min Act: -0.1700
Data Index: 594138 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1526. Min Range: -4.1526
Max Act: 4.0588. Min Act: -0.1700
Data Index: 3308923 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1526. Min Range: -4.1526
Max Act: 4.1213. Min Act: -0.1700
Data Index: 5170946 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.9963. Min Act: -0.1700
Data Index: 2257596 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1526. Min Range: -4.1526
Max Act: 4.0275. Min Act: -0.1700
Data Index: 1042686 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.9650. Min Act: -0.1700
Data Index: 1450498 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.9963. Min Act: -0.1700
Data Index: 6665327 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.9337. Min Act: -0.1700
Data Index: 772087 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.9025. Min Act: -0.1700
Data Index: 1705450 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.9337. Min Act: -0.1700
Data Index: 2498015 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.9025. Min Act: -0.1700
Data Index: 1160784 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.9337. Min Act: -0.1700
Data Index: 3432576 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.8712. Min Act: -0.1700
Data Index: 2482806 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.8556. Min Act: -0.1700
Data Index: 7366013 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.8556. Min Act: -0.1700
Data Index: 1802826 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.8556. Min Act: -0.1700
Data Index: 8742291 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.8556. Min Act: -0.1700
Data Index: 5291307 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.8556. Min Act: -0.1700
Data Index: 1927797 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.8712. Min Act: -0.1700
Data Index: 8713510 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1526. Min Range: -4.1526
Max Act: 3.8087. Min Act: -0.1700
Data Index: 4859547 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19