Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1464. Min Range: -4.1464
Max Act: 4.1464. Min Act: -0.1700
Data Index: 2525932 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.8338. Min Act: -0.1700
Data Index: 8342816 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.8494. Min Act: -0.1700
Data Index: 2225969 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.8181. Min Act: -0.1700
Data Index: 5639297 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.8025. Min Act: -0.1700
Data Index: 7566175 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7869. Min Act: -0.1700
Data Index: 159573 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7869. Min Act: -0.1700
Data Index: 3627526 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7556. Min Act: -0.1700
Data Index: 1680388 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7869. Min Act: -0.1700
Data Index: 2835923 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7556. Min Act: -0.1700
Data Index: 7697280 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7556. Min Act: -0.1700
Data Index: 2063168 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7712. Min Act: -0.1700
Data Index: 4290335 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7556. Min Act: -0.1700
Data Index: 745382 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7399. Min Act: -0.1700
Data Index: 2426637 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7399. Min Act: -0.1700
Data Index: 436649 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7399. Min Act: -0.1700
Data Index: 298915 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7556. Min Act: -0.1700
Data Index: 987067 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7243. Min Act: -0.1700
Data Index: 7900731 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7243. Min Act: -0.1700
Data Index: 1912147 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1464. Min Range: -4.1464
Max Act: 3.7087. Min Act: -0.1700
Data Index: 265588 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19