Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4067 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.9524. Min Act: -0.1700
Data Index: 5298561 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.8899. Min Act: -0.1700
Data Index: 901656 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.8899. Min Act: -0.1700
Data Index: 6280559 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.8274. Min Act: -0.1700
Data Index: 406895 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.8587. Min Act: -0.1700
Data Index: 1712831 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.8274. Min Act: -0.1700
Data Index: 6545664 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.8274. Min Act: -0.1700
Data Index: 1751753 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.7962. Min Act: -0.1700
Data Index: 784528 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.7337. Min Act: -0.1700
Data Index: 6819973 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6712. Min Act: -0.1700
Data Index: 4202519 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.7024. Min Act: -0.1700
Data Index: 4076571 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6712. Min Act: -0.1700
Data Index: 6802728 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6712. Min Act: -0.1700
Data Index: 8207016 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6712. Min Act: -0.1700
Data Index: 2669825 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6399. Min Act: -0.1700
Data Index: 6043771 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6399. Min Act: -0.1700
Data Index: 6043770 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6399. Min Act: -0.1700
Data Index: 7093699 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6399. Min Act: -0.1700
Data Index: 6993314 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6399. Min Act: -0.1700
Data Index: 6020653 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9524. Min Range: -4.9524
Max Act: 4.6399. Min Act: -0.1700
Data Index: 5768975 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19