Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.7437. Min Act: -0.1700
Data Index: 6996093 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.7437. Min Act: -0.1700
Data Index: 2406950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.7437. Min Act: -0.1700
Data Index: 5404575 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.6957. Min Act: -0.1700
Data Index: 3874599 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.6797. Min Act: -0.1700
Data Index: 3830235 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.6476. Min Act: -0.1700
Data Index: 7880121 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.6155. Min Act: -0.1700
Data Index: 2610456 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.6316. Min Act: -0.1700
Data Index: 1815779 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.6476. Min Act: -0.1700
Data Index: 3786161 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.6155. Min Act: -0.1700
Data Index: 2590877 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.6155. Min Act: -0.1699
Data Index: 1501916 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.5833. Min Act: -0.1700
Data Index: 6757978 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.5994. Min Act: -0.1700
Data Index: 886371 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.5994. Min Act: -0.1700
Data Index: 867272 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.5833. Min Act: -0.1700
Data Index: 1609656 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.5672. Min Act: -0.1700
Data Index: 5063272 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.5833. Min Act: -0.1700
Data Index: 1289076 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.5672. Min Act: -0.1700
Data Index: 8023132 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.5672. Min Act: -0.1700
Data Index: 5156770 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7437. Min Range: -2.7437
Max Act: 2.5672. Min Act: -0.1700
Data Index: 4273671 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19