Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 581 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.3009. Min Act: -0.1700
Data Index: 4967487 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.1446. Min Act: -0.1700
Data Index: 2793214 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.1446. Min Act: -0.1700
Data Index: 873793 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0821. Min Act: -0.1700
Data Index: 2032352 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.1134. Min Act: -0.1700
Data Index: 964698 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.1134. Min Act: -0.1700
Data Index: 5832485 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.1134. Min Act: -0.1700
Data Index: 2261142 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.1134. Min Act: -0.1700
Data Index: 2051682 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0821. Min Act: -0.1700
Data Index: 4549401 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0821. Min Act: -0.1700
Data Index: 3958817 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.1134. Min Act: -0.1700
Data Index: 5382195 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0508. Min Act: -0.1700
Data Index: 2616946 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0196. Min Act: -0.1700
Data Index: 5261208 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0508. Min Act: -0.1700
Data Index: 8153460 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0508. Min Act: -0.1700
Data Index: 2530277 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0196. Min Act: -0.1700
Data Index: 1769262 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0196. Min Act: -0.1700
Data Index: 7024553 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3009. Min Range: -4.3009
Max Act: 3.9883. Min Act: -0.1700
Data Index: 6078416 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0196. Min Act: -0.1700
Data Index: 2390395 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3009. Min Range: -4.3009
Max Act: 4.0196. Min Act: -0.1700
Data Index: 939031 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19