Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2862 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.9009. Min Act: -0.1700
Data Index: 4745102 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.8384. Min Act: -0.1700
Data Index: 4924059 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.8384. Min Act: -0.1700
Data Index: 7586714 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.7759. Min Act: -0.1700
Data Index: 8628516 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.7134. Min Act: -0.1700
Data Index: 7313890 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.7134. Min Act: -0.1700
Data Index: 7862021 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.6821. Min Act: -0.1700
Data Index: 216584 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.6821. Min Act: -0.1700
Data Index: 6680007 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.6509. Min Act: -0.1700
Data Index: 5191207 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.6196. Min Act: -0.1700
Data Index: 7839480 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.6196. Min Act: -0.1700
Data Index: 1115317 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.5571. Min Act: -0.1700
Data Index: 1151215 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.5571. Min Act: -0.1700
Data Index: 7153262 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.5571. Min Act: -0.1700
Data Index: 8638596 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.5884. Min Act: -0.1700
Data Index: 4899402 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.6196. Min Act: -0.1700
Data Index: 4314884 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.5259. Min Act: -0.1700
Data Index: 874655 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.5884. Min Act: -0.1700
Data Index: 6932624 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.5259. Min Act: -0.1700
Data Index: 7828857 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9009. Min Range: -5.9009
Max Act: 5.5571. Min Act: -0.1700
Data Index: 59061 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19