Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4047 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.9370. Min Act: -0.1700
Data Index: 791013 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.9200. Min Act: -0.1700
Data Index: 2469590 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.8517. Min Act: -0.1700
Data Index: 548696 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.8346. Min Act: -0.1700
Data Index: 441218 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.8088. Min Act: -0.1700
Data Index: 1999722 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.8088. Min Act: -0.1700
Data Index: 5627485 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.8002. Min Act: -0.1700
Data Index: 6241670 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7916. Min Act: -0.1700
Data Index: 2948166 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7830. Min Act: -0.1700
Data Index: 8398591 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7658. Min Act: -0.1700
Data Index: 6387888 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7658. Min Act: -0.1700
Data Index: 1773124 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7571. Min Act: -0.1700
Data Index: 3553414 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7571. Min Act: -0.1700
Data Index: 5339430 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7571. Min Act: -0.1700
Data Index: 357713 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7571. Min Act: -0.1700
Data Index: 7896365 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7658. Min Act: -0.1700
Data Index: 8742081 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7571. Min Act: -0.1700
Data Index: 4073772 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7571. Min Act: -0.1700
Data Index: 8672187 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7485. Min Act: -0.1700
Data Index: 190736 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9370. Min Range: -1.9370
Max Act: 1.7485. Min Act: -0.1699
Data Index: 6806135 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19