Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2026. Min Range: -4.2026
Max Act: 4.1714. Min Act: -0.1700
Data Index: 857108 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2026. Min Range: -4.2026
Max Act: 4.1714. Min Act: -0.1700
Data Index: 7383101 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2026. Min Range: -4.2026
Max Act: 4.2026. Min Act: -0.1700
Data Index: 5768384 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2026. Min Range: -4.2026
Max Act: 4.1088. Min Act: -0.1700
Data Index: 7088965 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2026. Min Range: -4.2026
Max Act: 4.0463. Min Act: -0.1700
Data Index: 8020578 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2026. Min Range: -4.2026
Max Act: 4.0151. Min Act: -0.1700
Data Index: 1916490 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2026. Min Range: -4.2026
Max Act: 4.0151. Min Act: -0.1700
Data Index: 3378856 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9525. Min Act: -0.1700
Data Index: 5264880 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2026. Min Range: -4.2026
Max Act: 4.0151. Min Act: -0.1700
Data Index: 3269430 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9838. Min Act: -0.1700
Data Index: 5215346 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9838. Min Act: -0.1700
Data Index: 6183478 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9838. Min Act: -0.1700
Data Index: 5722946 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2026. Min Range: -4.2026
Max Act: 4.0151. Min Act: -0.1700
Data Index: 5300438 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9838. Min Act: -0.1700
Data Index: 160820 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9838. Min Act: -0.1700
Data Index: 397056 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9525. Min Act: -0.1700
Data Index: 1823978 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9525. Min Act: -0.1700
Data Index: 6449054 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9525. Min Act: -0.1700
Data Index: 2989313 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9525. Min Act: -0.1700
Data Index: 6405931 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2026. Min Range: -4.2026
Max Act: 3.9213. Min Act: -0.1700
Data Index: 6358130 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19