Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2332 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.0737. Min Range: -5.0737
Max Act: 5.0737. Min Act: -0.1700
Data Index: 6015825 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.8549. Min Act: -0.1700
Data Index: 5670695 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.8237. Min Act: -0.1700
Data Index: 8269986 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.7612. Min Act: -0.1700
Data Index: 95587 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.7299. Min Act: -0.1700
Data Index: 7078378 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.6987. Min Act: -0.1700
Data Index: 3984259 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.6674. Min Act: -0.1700
Data Index: 8740777 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.6674. Min Act: -0.1700
Data Index: 2370858 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.6674. Min Act: -0.1700
Data Index: 2150450 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.6362. Min Act: -0.1700
Data Index: 6421679 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.6049. Min Act: -0.1700
Data Index: 4734680 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.6049. Min Act: -0.1700
Data Index: 3509079 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.6049. Min Act: -0.1700
Data Index: 5944553 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.5737. Min Act: -0.1700
Data Index: 5854697 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.5737. Min Act: -0.1700
Data Index: 4274108 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.5737. Min Act: -0.1700
Data Index: 682215 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.5737. Min Act: -0.1700
Data Index: 3605451 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.5737. Min Act: -0.1700
Data Index: 1865441 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.5737. Min Act: -0.1700
Data Index: 2814270 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0737. Min Range: -5.0737
Max Act: 4.6049. Min Act: -0.1700
Data Index: 1865442 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19