Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0306. Min Range: -7.0306
Max Act: 7.0306. Min Act: -0.1700
Data Index: 375911 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.9369. Min Act: -0.1700
Data Index: 8526998 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.8744. Min Act: -0.1700
Data Index: 8600126 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.8744. Min Act: -0.1700
Data Index: 4289543 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.8431. Min Act: -0.1700
Data Index: 3796139 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.8431. Min Act: -0.1700
Data Index: 6330018 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.8431. Min Act: -0.1700
Data Index: 1941731 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.8119. Min Act: -0.1700
Data Index: 1654679 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.7494. Min Act: -0.1700
Data Index: 8000002 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.7494. Min Act: -0.1700
Data Index: 5827170 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.7806. Min Act: -0.1700
Data Index: 3135765 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.7181. Min Act: -0.1700
Data Index: 3135767 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.6556. Min Act: -0.1700
Data Index: 8527000 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.6556. Min Act: -0.1700
Data Index: 4749273 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.6869. Min Act: -0.1700
Data Index: 375921 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.6244. Min Act: -0.1700
Data Index: 1833591 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.5619. Min Act: -0.1700
Data Index: 8526992 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.5619. Min Act: -0.1700
Data Index: 6292064 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.5619. Min Act: -0.1700
Data Index: 8000000 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.5619. Min Act: -0.1700
Data Index: 8028587 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19