Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 820 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.5309. Min Act: -0.1700
Data Index: 4360270 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.4059. Min Act: -0.1700
Data Index: 8365858 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.3746. Min Act: -0.1700
Data Index: 7777680 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.4059. Min Act: -0.1700
Data Index: 4843647 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.3746. Min Act: -0.1700
Data Index: 6549081 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.3434. Min Act: -0.1700
Data Index: 1810467 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.3121. Min Act: -0.1700
Data Index: 7543342 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.2809. Min Act: -0.1700
Data Index: 3596897 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.2496. Min Act: -0.1700
Data Index: 2366983 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.2184. Min Act: -0.1700
Data Index: 5887536 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.2184. Min Act: -0.1700
Data Index: 2845969 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.1871. Min Act: -0.1700
Data Index: 4943718 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.1871. Min Act: -0.1700
Data Index: 1620458 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.1871. Min Act: -0.1700
Data Index: 3619325 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.1559. Min Act: -0.1700
Data Index: 4429109 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.1246. Min Act: -0.1700
Data Index: 4829398 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.1246. Min Act: -0.1700
Data Index: 8359342 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.0934. Min Act: -0.1700
Data Index: 5075393 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.0934. Min Act: -0.1700
Data Index: 2915437 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5309. Min Range: -4.5309
Max Act: 4.0934. Min Act: -0.1700
Data Index: 3614140 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19