Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.6860. Min Act: -0.1700
Data Index: 7817521 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.5295. Min Act: -0.1700
Data Index: 1702785 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.5295. Min Act: -0.1700
Data Index: 7817525 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.5295. Min Act: -0.1700
Data Index: 8137965 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.5295. Min Act: -0.1700
Data Index: 6561641 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.5295. Min Act: -0.1700
Data Index: 3305993 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4982. Min Act: -0.1700
Data Index: 3584605 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4982. Min Act: -0.1700
Data Index: 3838450 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4669. Min Act: -0.1700
Data Index: 8603257 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4982. Min Act: -0.1700
Data Index: 7447372 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4982. Min Act: -0.1700
Data Index: 6461972 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4982. Min Act: -0.1700
Data Index: 6383365 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4669. Min Act: -0.1700
Data Index: 3551674 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4669. Min Act: -0.1700
Data Index: 7111441 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4669. Min Act: -0.1700
Data Index: 921967 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4669. Min Act: -0.1700
Data Index: 5724618 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4669. Min Act: -0.1700
Data Index: 5554305 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4669. Min Act: -0.1700
Data Index: 5059237 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4669. Min Act: -0.1700
Data Index: 2687200 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6860. Min Range: -3.6860
Max Act: 3.4669. Min Act: -0.1700
Data Index: 2515695 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19