Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.9333. Min Act: -0.1700
Data Index: 7521325 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.7770. Min Act: -0.1700
Data Index: 504397 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.7770. Min Act: -0.1700
Data Index: 7199731 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.8083. Min Act: -0.1700
Data Index: 5994158 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.7770. Min Act: -0.1700
Data Index: 4103209 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.6520. Min Act: -0.1700
Data Index: 6027153 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.6208. Min Act: -0.1700
Data Index: 6269710 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.6208. Min Act: -0.1700
Data Index: 5531997 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.6208. Min Act: -0.1700
Data Index: 5369560 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.5895. Min Act: -0.1700
Data Index: 7840548 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.5895. Min Act: -0.1700
Data Index: 6395088 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.5270. Min Act: -0.1700
Data Index: 2414808 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4958. Min Act: -0.1700
Data Index: 5594432 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.5270. Min Act: -0.1700
Data Index: 5970134 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.5583. Min Act: -0.1700
Data Index: 3828644 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4958. Min Act: -0.1700
Data Index: 3541043 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4645. Min Act: -0.1700
Data Index: 8122627 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4958. Min Act: -0.1700
Data Index: 8824225 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4958. Min Act: -0.1700
Data Index: 6106848 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4333. Min Act: -0.1700
Data Index: 7346297 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19