Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4191 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.2422. Min Act: -0.1700
Data Index: 6214460 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.1797. Min Act: -0.1700
Data Index: 7675395 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.1484. Min Act: -0.1700
Data Index: 4745983 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.1172. Min Act: -0.1700
Data Index: 8497459 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.1484. Min Act: -0.1700
Data Index: 1898070 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.0859. Min Act: -0.1700
Data Index: 2930990 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.0859. Min Act: -0.1700
Data Index: 2410427 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.0547. Min Act: -0.1700
Data Index: 6695987 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.0859. Min Act: -0.1700
Data Index: 768570 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2422. Min Range: -5.2422
Max Act: 4.9922. Min Act: -0.1700
Data Index: 4881637 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.0234. Min Act: -0.1700
Data Index: 6655683 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2422. Min Range: -5.2422
Max Act: 4.9922. Min Act: -0.1700
Data Index: 2806221 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2422. Min Range: -5.2422
Max Act: 4.9609. Min Act: -0.1700
Data Index: 4684511 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2422. Min Range: -5.2422
Max Act: 5.0234. Min Act: -0.1700
Data Index: 7685977 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2422. Min Range: -5.2422
Max Act: 4.9609. Min Act: -0.1700
Data Index: 5375607 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2422. Min Range: -5.2422
Max Act: 4.9609. Min Act: -0.1700
Data Index: 4159471 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2422. Min Range: -5.2422
Max Act: 4.9297. Min Act: -0.1700
Data Index: 2600407 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2422. Min Range: -5.2422
Max Act: 4.9609. Min Act: -0.1700
Data Index: 3037114 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2422. Min Range: -5.2422
Max Act: 4.9297. Min Act: -0.1700
Data Index: 1898792 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2422. Min Range: -5.2422
Max Act: 4.9609. Min Act: -0.1700
Data Index: 63721 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19