Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3983 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.4389. Min Act: -0.1700
Data Index: 7459145 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.3451. Min Act: -0.1700
Data Index: 1884421 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.2826. Min Act: -0.1700
Data Index: 1884428 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.2826. Min Act: -0.1700
Data Index: 3171873 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.2201. Min Act: -0.1700
Data Index: 2098795 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.2201. Min Act: -0.1700
Data Index: 2098797 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.1889. Min Act: -0.1700
Data Index: 1332407 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0951. Min Act: -0.1700
Data Index: 2999874 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0951. Min Act: -0.1700
Data Index: 823869 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0951. Min Act: -0.1700
Data Index: 2098796 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0951. Min Act: -0.1700
Data Index: 1884426 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0639. Min Act: -0.1700
Data Index: 977955 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0639. Min Act: -0.1700
Data Index: 1884425 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0014. Min Act: -0.1700
Data Index: 2098794 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0014. Min Act: -0.1700
Data Index: 5859345 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4389. Min Range: -5.4389
Max Act: 4.9701. Min Act: -0.1700
Data Index: 7382382 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0014. Min Act: -0.1700
Data Index: 1884427 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0014. Min Act: -0.1700
Data Index: 5893956 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4389. Min Range: -5.4389
Max Act: 5.0326. Min Act: -0.1700
Data Index: 3224892 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4389. Min Range: -5.4389
Max Act: 4.9701. Min Act: -0.1700
Data Index: 3366460 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19