Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.5914. Min Act: -0.1700
Data Index: 4573611 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.5289. Min Act: -0.1700
Data Index: 3941514 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4976. Min Act: -0.1700
Data Index: 6116843 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4664. Min Act: -0.1700
Data Index: 7847376 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4351. Min Act: -0.1700
Data Index: 3253239 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.3726. Min Act: -0.1700
Data Index: 5633704 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4351. Min Act: -0.1700
Data Index: 5815973 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4351. Min Act: -0.1700
Data Index: 727780 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.4039. Min Act: -0.1700
Data Index: 658613 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.3414. Min Act: -0.1700
Data Index: 5850582 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.3726. Min Act: -0.1700
Data Index: 8233809 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.3414. Min Act: -0.1700
Data Index: 5398986 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.3414. Min Act: -0.1700
Data Index: 6258330 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.3726. Min Act: -0.1700
Data Index: 1796436 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.3726. Min Act: -0.1700
Data Index: 4700839 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.3101. Min Act: -0.1700
Data Index: 7922811 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.2789. Min Act: -0.1700
Data Index: 6219066 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.3101. Min Act: -0.1700
Data Index: 1149047 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.2789. Min Act: -0.1700
Data Index: 7353697 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5914. Min Range: -4.5914
Max Act: 4.2789. Min Act: -0.1700
Data Index: 1648304 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19