Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2105 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.3988. Min Act: -0.1700
Data Index: 3278428 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.4300. Min Act: -0.1700
Data Index: 4671986 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.3675. Min Act: -0.1700
Data Index: 3140262 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.3675. Min Act: -0.1700
Data Index: 5081531 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.3050. Min Act: -0.1700
Data Index: 343959 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.2738. Min Act: -0.1700
Data Index: 1403824 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.2738. Min Act: -0.1700
Data Index: 7304717 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.2738. Min Act: -0.1700
Data Index: 4760102 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.2113. Min Act: -0.1700
Data Index: 130533 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.2425. Min Act: -0.1700
Data Index: 6574193 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.2425. Min Act: -0.1700
Data Index: 3050976 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.2113. Min Act: -0.1700
Data Index: 975660 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.1488. Min Act: -0.1700
Data Index: 4402173 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.1800. Min Act: -0.1700
Data Index: 5359265 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.1800. Min Act: -0.1700
Data Index: 2215961 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.1488. Min Act: -0.1700
Data Index: 502040 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.1800. Min Act: -0.1700
Data Index: 4769146 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.1175. Min Act: -0.1700
Data Index: 1214041 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.1488. Min Act: -0.1700
Data Index: 6575592 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4300. Min Range: -6.4300
Max Act: 6.1488. Min Act: -0.1700
Data Index: 7228822 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19