Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.4424. Min Act: -0.1700
Data Index: 2944743 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.4262. Min Act: -0.1700
Data Index: 4178901 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.3445. Min Act: -0.1700
Data Index: 5928575 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2787. Min Act: -0.1700
Data Index: 7735652 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2787. Min Act: -0.1700
Data Index: 7939652 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2787. Min Act: -0.1700
Data Index: 3050238 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2787. Min Act: -0.1700
Data Index: 3452561 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2457. Min Act: -0.1700
Data Index: 7500777 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2622. Min Act: -0.1700
Data Index: 2328262 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2457. Min Act: -0.1700
Data Index: 3542369 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2622. Min Act: -0.1700
Data Index: 8195726 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2457. Min Act: -0.1700
Data Index: 6888381 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2622. Min Act: -0.1700
Data Index: 8622484 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2457. Min Act: -0.1700
Data Index: 756457 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2622. Min Act: -0.1700
Data Index: 7903991 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2457. Min Act: -0.1700
Data Index: 4443732 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2292. Min Act: -0.1700
Data Index: 5472907 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2126. Min Act: -0.1700
Data Index: 7559298 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2126. Min Act: -0.1700
Data Index: 3720183 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2292. Min Act: -0.1700
Data Index: 3744255 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19