Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.9414. Min Act: -0.1700
Data Index: 3083817 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.9102. Min Act: -0.1700
Data Index: 7841027 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.8789. Min Act: -0.1700
Data Index: 5661808 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.8164. Min Act: -0.1700
Data Index: 7652454 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.7227. Min Act: -0.1700
Data Index: 3854411 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.7227. Min Act: -0.1700
Data Index: 5661801 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.6602. Min Act: -0.1700
Data Index: 678563 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.6602. Min Act: -0.1700
Data Index: 6446440 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.6602. Min Act: -0.1700
Data Index: 7838593 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.6602. Min Act: -0.1700
Data Index: 5027734 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.6289. Min Act: -0.1700
Data Index: 2612847 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.6289. Min Act: -0.1700
Data Index: 1768863 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.5664. Min Act: -0.1700
Data Index: 5661798 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.5352. Min Act: -0.1700
Data Index: 191048 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.5664. Min Act: -0.1700
Data Index: 4682705 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.5352. Min Act: -0.1700
Data Index: 1273168 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.5664. Min Act: -0.1700
Data Index: 2585580 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.5664. Min Act: -0.1700
Data Index: 2688177 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.5352. Min Act: -0.1700
Data Index: 5694112 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9414. Min Range: -5.9414
Max Act: 5.5039. Min Act: -0.1700
Data Index: 830948 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19