Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3042 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.3696. Min Act: -0.1700
Data Index: 3276506 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.3383. Min Act: -0.1700
Data Index: 4254836 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2758. Min Act: -0.1700
Data Index: 8004262 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2758. Min Act: -0.1700
Data Index: 655534 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2758. Min Act: -0.1700
Data Index: 2587527 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.3071. Min Act: -0.1700
Data Index: 8483668 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2758. Min Act: -0.1700
Data Index: 2790146 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2758. Min Act: -0.1700
Data Index: 5706853 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2446. Min Act: -0.1700
Data Index: 8822876 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2758. Min Act: -0.1700
Data Index: 5753097 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2133. Min Act: -0.1700
Data Index: 4587454 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2446. Min Act: -0.1700
Data Index: 2459536 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2446. Min Act: -0.1700
Data Index: 7790996 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.2133. Min Act: -0.1700
Data Index: 4765057 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.1196. Min Act: -0.1700
Data Index: 4112145 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.1821. Min Act: -0.1700
Data Index: 2261469 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.1821. Min Act: -0.1700
Data Index: 3137138 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.1821. Min Act: -0.1700
Data Index: 4176268 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.1508. Min Act: -0.1700
Data Index: 3748821 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3696. Min Range: -4.3696
Max Act: 4.1508. Min Act: -0.1699
Data Index: 668136 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19