Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.9331. Min Act: -0.1700
Data Index: 297314 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.8862. Min Act: -0.1700
Data Index: 126760 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.8393. Min Act: -0.1700
Data Index: 4082843 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.8081. Min Act: -0.1700
Data Index: 1870095 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7768. Min Act: -0.1700
Data Index: 8330124 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7924. Min Act: -0.1700
Data Index: 3296691 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7768. Min Act: -0.1700
Data Index: 6831594 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7611. Min Act: -0.1700
Data Index: 6433278 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7455. Min Act: -0.1700
Data Index: 4288948 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7611. Min Act: -0.1700
Data Index: 1580781 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7768. Min Act: -0.1700
Data Index: 8560955 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7455. Min Act: -0.1700
Data Index: 7122995 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7455. Min Act: -0.1700
Data Index: 1841631 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7142. Min Act: -0.1700
Data Index: 2602087 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7142. Min Act: -0.1700
Data Index: 8399382 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7142. Min Act: -0.1700
Data Index: 344042 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7142. Min Act: -0.1700
Data Index: 7874031 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7142. Min Act: -0.1700
Data Index: 2038087 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.6986. Min Act: -0.1700
Data Index: 1070705 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9331. Min Range: -3.9331
Max Act: 3.7142. Min Act: -0.1700
Data Index: 540354 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19