Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.5325. Min Act: -0.1700
Data Index: 3410947 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.3762. Min Act: -0.1700
Data Index: 7386297 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.3450. Min Act: -0.1700
Data Index: 6075960 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2825. Min Act: -0.1699
Data Index: 7670510 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.3137. Min Act: -0.1700
Data Index: 1593327 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.3137. Min Act: -0.1700
Data Index: 1254864 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2825. Min Act: -0.1700
Data Index: 2686907 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2825. Min Act: -0.1700
Data Index: 7149222 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2825. Min Act: -0.1700
Data Index: 7756079 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2825. Min Act: -0.1700
Data Index: 6047150 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2825. Min Act: -0.1700
Data Index: 3045587 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2825. Min Act: -0.1700
Data Index: 6648618 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2825. Min Act: -0.1700
Data Index: 4015409 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2825. Min Act: -0.1700
Data Index: 8134475 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2512. Min Act: -0.1700
Data Index: 7066869 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2512. Min Act: -0.1700
Data Index: 2158178 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2512. Min Act: -0.1700
Data Index: 8069557 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2512. Min Act: -0.1700
Data Index: 6165585 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2512. Min Act: -0.1700
Data Index: 1847997 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5325. Min Range: -4.5325
Max Act: 4.2200. Min Act: -0.1700
Data Index: 1531009 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19