Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.7411. Min Act: -0.1700
Data Index: 3742960 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.7099. Min Act: -0.1700
Data Index: 8708310 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.6786. Min Act: -0.1700
Data Index: 7309864 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.6161. Min Act: -0.1700
Data Index: 295278 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.6474. Min Act: -0.1700
Data Index: 5096762 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5849. Min Act: -0.1700
Data Index: 140513 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5224. Min Act: -0.1700
Data Index: 7610749 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 7947346 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5224. Min Act: -0.1700
Data Index: 5617867 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 5090646 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 4710309 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5224. Min Act: -0.1700
Data Index: 1257120 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4599. Min Act: -0.1700
Data Index: 844707 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 7088447 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4599. Min Act: -0.1700
Data Index: 8155342 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4599. Min Act: -0.1700
Data Index: 8815039 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4599. Min Act: -0.1700
Data Index: 4657170 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.3974. Min Act: -0.1700
Data Index: 1032605 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4599. Min Act: -0.1700
Data Index: 2097133 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4286. Min Act: -0.1700
Data Index: 7474650 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19