Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7537. Min Act: -0.1700
Data Index: 4794566 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7364. Min Act: -0.1700
Data Index: 2700503 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7018. Min Act: -0.1700
Data Index: 2682416 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7018. Min Act: -0.1700
Data Index: 7989227 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6845. Min Act: -0.1700
Data Index: 8087718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6584. Min Act: -0.1700
Data Index: 6592607 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6497. Min Act: -0.1699
Data Index: 8229520 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6671. Min Act: -0.1700
Data Index: 8551933 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6497. Min Act: -0.1700
Data Index: 2331661 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6410. Min Act: -0.1692
Data Index: 7430652 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6323. Min Act: -0.1700
Data Index: 8006339 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6235. Min Act: -0.1700
Data Index: 636234 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6235. Min Act: -0.1700
Data Index: 8000836 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6323. Min Act: -0.1700
Data Index: 2634177 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6410. Min Act: -0.1700
Data Index: 4679394 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6235. Min Act: -0.1700
Data Index: 2786517 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6235. Min Act: -0.1700
Data Index: 6279125 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6148. Min Act: -0.1700
Data Index: 2677133 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6061. Min Act: -0.1700
Data Index: 2020179 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6235. Min Act: -0.1700
Data Index: 243191 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19