Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.6973. Min Act: -0.1700
Data Index: 8267635 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.6661. Min Act: -0.1700
Data Index: 5494079 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.6348. Min Act: -0.1700
Data Index: 8267634 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.6348. Min Act: -0.1700
Data Index: 3909750 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.6348. Min Act: -0.1700
Data Index: 3481616 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.5098. Min Act: -0.1700
Data Index: 2742990 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.5098. Min Act: -0.1700
Data Index: 1015950 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.4473. Min Act: -0.1700
Data Index: 888140 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.4160. Min Act: -0.1700
Data Index: 8525163 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.3848. Min Act: -0.1700
Data Index: 8036734 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.3223. Min Act: -0.1700
Data Index: 8036735 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.2598. Min Act: -0.1700
Data Index: 5871104 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.3223. Min Act: -0.1700
Data Index: 9171 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.2598. Min Act: -0.1700
Data Index: 4445562 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.2598. Min Act: -0.1700
Data Index: 5449891 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.2285. Min Act: -0.1700
Data Index: 4849457 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.2285. Min Act: -0.1700
Data Index: 1753970 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.2285. Min Act: -0.1700
Data Index: 5871105 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.2285. Min Act: -0.1700
Data Index: 8525161 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6973. Min Range: -4.6973
Max Act: 4.2285. Min Act: -0.1700
Data Index: 7205938 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19