Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3811 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.5022. Min Act: -0.1700
Data Index: 6146090 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.4396. Min Act: -0.1700
Data Index: 7014868 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.4396. Min Act: -0.1700
Data Index: 3355467 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.4082. Min Act: -0.1700
Data Index: 1638352 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.4239. Min Act: -0.1700
Data Index: 1251442 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3768. Min Act: -0.1700
Data Index: 7193243 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3768. Min Act: -0.1700
Data Index: 8742215 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3768. Min Act: -0.1700
Data Index: 8212544 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3298. Min Act: -0.1700
Data Index: 8212542 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3455. Min Act: -0.1700
Data Index: 5033968 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3612. Min Act: -0.1700
Data Index: 5845153 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3455. Min Act: -0.1700
Data Index: 8204113 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3298. Min Act: -0.1700
Data Index: 5733810 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2984. Min Act: -0.1700
Data Index: 8142360 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2984. Min Act: -0.1700
Data Index: 8742197 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3141. Min Act: -0.1700
Data Index: 6529398 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2984. Min Act: -0.1700
Data Index: 5388768 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3298. Min Act: -0.1700
Data Index: 891492 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2670. Min Act: -0.1700
Data Index: 441846 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2827. Min Act: -0.1700
Data Index: 6253000 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19