Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 564 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1847. Min Range: -8.1847
Max Act: 8.1847. Min Act: -0.1700
Data Index: 7366348 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1847. Min Range: -8.1847
Max Act: 8.0597. Min Act: -0.1700
Data Index: 6529114 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1847. Min Range: -8.1847
Max Act: 8.0597. Min Act: -0.1700
Data Index: 827492 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.9659. Min Act: -0.1700
Data Index: 5341904 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.9659. Min Act: -0.1700
Data Index: 1203743 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8722. Min Act: -0.1700
Data Index: 7619691 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8722. Min Act: -0.1700
Data Index: 5838441 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8722. Min Act: -0.1700
Data Index: 6626943 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8409. Min Act: -0.1700
Data Index: 3728540 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8409. Min Act: -0.1700
Data Index: 3508668 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.9034. Min Act: -0.1700
Data Index: 8177848 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8722. Min Act: -0.1700
Data Index: 84822 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8097. Min Act: -0.1700
Data Index: 85421 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8097. Min Act: -0.1700
Data Index: 5441794 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8097. Min Act: -0.1700
Data Index: 8824364 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.8097. Min Act: -0.1700
Data Index: 4512402 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.7784. Min Act: -0.1700
Data Index: 2720586 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.7472. Min Act: -0.1700
Data Index: 7766167 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.7159. Min Act: -0.1700
Data Index: 3003477 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1847. Min Range: -8.1847
Max Act: 7.7159. Min Act: -0.1700
Data Index: 4561232 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19