Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.8226. Min Act: -0.1700
Data Index: 1495148 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6950. Min Act: -0.1700
Data Index: 2537257 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6950. Min Act: -0.1700
Data Index: 7753236 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6469. Min Act: -0.1700
Data Index: 8170863 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6469. Min Act: -0.1700
Data Index: 7650821 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6469. Min Act: -0.1700
Data Index: 1703070 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6469. Min Act: -0.1700
Data Index: 6879538 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6469. Min Act: -0.1700
Data Index: 6806778 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6308. Min Act: -0.1700
Data Index: 7539130 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6469. Min Act: -0.1700
Data Index: 5943592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.5664. Min Act: -0.1700
Data Index: 5157219 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6147. Min Act: -0.1700
Data Index: 7881365 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6147. Min Act: -0.1700
Data Index: 779831 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.5987. Min Act: -0.1700
Data Index: 7191673 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6147. Min Act: -0.1700
Data Index: 5078008 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.5826. Min Act: -0.1700
Data Index: 4343573 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.6147. Min Act: -0.1700
Data Index: 7183429 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.5987. Min Act: -0.1700
Data Index: 4158607 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.5826. Min Act: -0.1700
Data Index: 5986144 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8226. Min Range: -2.8226
Max Act: 2.5503. Min Act: -0.1700
Data Index: 900161 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19