Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 496 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1134. Min Range: -5.1134
Max Act: 5.1134. Min Act: -0.1700
Data Index: 8055539 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1134. Min Range: -5.1134
Max Act: 5.0196. Min Act: -0.1700
Data Index: 239849 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.9884. Min Act: -0.1700
Data Index: 3028850 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.9259. Min Act: -0.1700
Data Index: 6896220 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.9259. Min Act: -0.1700
Data Index: 8197122 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8946. Min Act: -0.1700
Data Index: 7225624 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8634. Min Act: -0.1700
Data Index: 370437 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 3494446 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8634. Min Act: -0.1700
Data Index: 6394783 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 4394902 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 4734016 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 7663072 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 2045350 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 1442698 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 6781644 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 6831141 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 899825 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 5008019 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 3956772 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 6711205 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19