Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.8578. Min Act: -0.1700
Data Index: 1310315 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.7016. Min Act: -0.1700
Data Index: 3335989 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6703. Min Act: -0.1700
Data Index: 2141600 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6703. Min Act: -0.1700
Data Index: 4037144 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6703. Min Act: -0.1700
Data Index: 638876 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6391. Min Act: -0.1700
Data Index: 5425025 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6391. Min Act: -0.1700
Data Index: 2331561 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6078. Min Act: -0.1700
Data Index: 4784556 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6078. Min Act: -0.1700
Data Index: 5418466 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6078. Min Act: -0.1700
Data Index: 5441146 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6078. Min Act: -0.1700
Data Index: 1700911 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.5766. Min Act: -0.1700
Data Index: 7726628 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.6078. Min Act: -0.1700
Data Index: 7412238 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.5766. Min Act: -0.1700
Data Index: 5814723 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.5766. Min Act: -0.1700
Data Index: 8605903 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.5766. Min Act: -0.1700
Data Index: 2596398 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.5766. Min Act: -0.1700
Data Index: 2057996 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.5453. Min Act: -0.1700
Data Index: 1694809 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.5453. Min Act: -0.1700
Data Index: 2796291 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8578. Min Range: -5.8578
Max Act: 5.5453. Min Act: -0.1700
Data Index: 3473289 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19