Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.5197. Min Act: -0.1700
Data Index: 2043224 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.4884. Min Act: -0.1700
Data Index: 1521594 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.4571. Min Act: -0.1700
Data Index: 2740910 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.4257. Min Act: -0.1700
Data Index: 2473151 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3944. Min Act: -0.1700
Data Index: 2818375 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3630. Min Act: -0.1700
Data Index: 1993841 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3473. Min Act: -0.1700
Data Index: 62182 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3473. Min Act: -0.1700
Data Index: 8622734 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3473. Min Act: -0.1700
Data Index: 7643962 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3316. Min Act: -0.1700
Data Index: 2559146 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3316. Min Act: -0.1700
Data Index: 6176216 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.2845. Min Act: -0.1700
Data Index: 2885442 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3002. Min Act: -0.1700
Data Index: 6277296 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3002. Min Act: -0.1700
Data Index: 8102992 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.3002. Min Act: -0.1700
Data Index: 6393274 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.2845. Min Act: -0.1700
Data Index: 448550 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.2845. Min Act: -0.1700
Data Index: 946934 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.2688. Min Act: -0.1700
Data Index: 3342572 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.2845. Min Act: -0.1700
Data Index: 7130805 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5197. Min Range: -3.5197
Max Act: 3.2688. Min Act: -0.1700
Data Index: 1071917 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19