Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1447 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.6140. Min Act: -0.1700
Data Index: 2569957 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.5200. Min Act: -0.1700
Data Index: 7890411 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.3162. Min Act: -0.1700
Data Index: 1705381 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2848. Min Act: -0.1700
Data Index: 130816 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.3005. Min Act: -0.1700
Data Index: 7211247 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2691. Min Act: -0.1700
Data Index: 3189892 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2691. Min Act: -0.1700
Data Index: 2359576 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2534. Min Act: -0.1700
Data Index: 4187161 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2220. Min Act: -0.1700
Data Index: 865317 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2534. Min Act: -0.1700
Data Index: 8162286 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2377. Min Act: -0.1700
Data Index: 8568033 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2220. Min Act: -0.1700
Data Index: 5418138 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2377. Min Act: -0.1700
Data Index: 3144982 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2220. Min Act: -0.1700
Data Index: 6388011 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2220. Min Act: -0.1700
Data Index: 1437538 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.2063. Min Act: -0.1700
Data Index: 3208957 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.1905. Min Act: -0.1700
Data Index: 561693 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.1748. Min Act: -0.1700
Data Index: 798610 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.1905. Min Act: -0.1700
Data Index: 5757353 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6140. Min Range: -3.6140
Max Act: 3.1748. Min Act: -0.1700
Data Index: 8074983 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19