Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 860 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.3548. Min Act: -0.1700
Data Index: 5217151 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.3236. Min Act: -0.1700
Data Index: 4692822 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.1673. Min Act: -0.1700
Data Index: 6049009 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.1361. Min Act: -0.1700
Data Index: 1473257 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.1361. Min Act: -0.1700
Data Index: 1750815 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.1048. Min Act: -0.1700
Data Index: 7562333 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.1048. Min Act: -0.1700
Data Index: 1077030 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0736. Min Act: -0.1700
Data Index: 1089955 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.1048. Min Act: -0.1700
Data Index: 3927942 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0423. Min Act: -0.1700
Data Index: 4396295 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.1048. Min Act: -0.1700
Data Index: 1203012 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0423. Min Act: -0.1700
Data Index: 3951809 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0423. Min Act: -0.1700
Data Index: 8517603 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0423. Min Act: -0.1700
Data Index: 4403262 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0111. Min Act: -0.1700
Data Index: 340448 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0423. Min Act: -0.1700
Data Index: 6625469 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0423. Min Act: -0.1700
Data Index: 4808134 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0111. Min Act: -0.1700
Data Index: 932625 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3548. Min Range: -5.3548
Max Act: 5.0423. Min Act: -0.1700
Data Index: 1187193 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3548. Min Range: -5.3548
Max Act: 4.9798. Min Act: -0.1700
Data Index: 5639052 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19