Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.9070. Min Act: -0.1700
Data Index: 3260772 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.8757. Min Act: -0.1700
Data Index: 7918642 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.8445. Min Act: -0.1700
Data Index: 7166360 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.8132. Min Act: -0.1700
Data Index: 8600217 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.7820. Min Act: -0.1700
Data Index: 3260773 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.8132. Min Act: -0.1700
Data Index: 6210000 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.8132. Min Act: -0.1700
Data Index: 6164709 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.7820. Min Act: -0.1700
Data Index: 8130887 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.7507. Min Act: -0.1700
Data Index: 4312822 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.7507. Min Act: -0.1700
Data Index: 5836860 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.7507. Min Act: -0.1700
Data Index: 1456811 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.6882. Min Act: -0.1700
Data Index: 1137696 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.6882. Min Act: -0.1700
Data Index: 4359947 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.6570. Min Act: -0.1700
Data Index: 1828772 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.6570. Min Act: -0.1700
Data Index: 7894409 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.6570. Min Act: -0.1700
Data Index: 1229858 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.6570. Min Act: -0.1700
Data Index: 4465514 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.6257. Min Act: -0.1700
Data Index: 3960005 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.6257. Min Act: -0.1700
Data Index: 3564288 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9070. Min Range: -5.9070
Max Act: 5.6570. Min Act: -0.1700
Data Index: 2008338 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19