Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2495 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.7316. Min Act: -0.1700
Data Index: 2910847 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.7316. Min Act: -0.1700
Data Index: 7546445 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.7316. Min Act: -0.1700
Data Index: 1478853 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.7316. Min Act: -0.1700
Data Index: 2280131 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.6378. Min Act: -0.1700
Data Index: 4215596 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.5128. Min Act: -0.1700
Data Index: 4257474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.5128. Min Act: -0.1700
Data Index: 7662105 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.5128. Min Act: -0.1700
Data Index: 1813121 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.5128. Min Act: -0.1700
Data Index: 1488873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.3878. Min Act: -0.1700
Data Index: 6265520 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.3878. Min Act: -0.1700
Data Index: 7149536 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.3878. Min Act: -0.1700
Data Index: 4228978 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.3253. Min Act: -0.1700
Data Index: 8209934 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.2941. Min Act: -0.1700
Data Index: 1820141 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.2941. Min Act: -0.1700
Data Index: 4133649 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.2941. Min Act: -0.1700
Data Index: 3068187 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.2941. Min Act: -0.1700
Data Index: 3619964 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.2941. Min Act: -0.1700
Data Index: 750862 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.2941. Min Act: -0.1700
Data Index: 1894820 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7316. Min Range: -4.7316
Max Act: 4.2941. Min Act: -0.1700
Data Index: 263555 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19