Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 526 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.6498. Min Act: -0.1700
Data Index: 2310178 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.4935. Min Act: -0.1700
Data Index: 4523038 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.4623. Min Act: -0.1700
Data Index: 3140210 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.4623. Min Act: -0.1700
Data Index: 3525863 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.4310. Min Act: -0.1700
Data Index: 5039133 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3997. Min Act: -0.1700
Data Index: 5064750 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3997. Min Act: -0.1700
Data Index: 1099910 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3685. Min Act: -0.1700
Data Index: 8186429 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3685. Min Act: -0.1700
Data Index: 2054747 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3685. Min Act: -0.1700
Data Index: 993334 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3685. Min Act: -0.1700
Data Index: 6948242 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3685. Min Act: -0.1700
Data Index: 2149599 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3685. Min Act: -0.1700
Data Index: 7529895 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3685. Min Act: -0.1700
Data Index: 5108423 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3372. Min Act: -0.1700
Data Index: 8530207 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3372. Min Act: -0.1700
Data Index: 5190929 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.2747. Min Act: -0.1700
Data Index: 4861335 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.2747. Min Act: -0.1700
Data Index: 1959697 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3060. Min Act: -0.1700
Data Index: 3583055 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6498. Min Range: -4.6498
Max Act: 4.3060. Min Act: -0.1700
Data Index: 2109221 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19