Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.5661. Min Act: -0.1696
Data Index: 2936312 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.4564. Min Act: -0.1700
Data Index: 4354626 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.4094. Min Act: -0.1644
Data Index: 5988517 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3937. Min Act: -0.1700
Data Index: 2520118 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3937. Min Act: -0.1697
Data Index: 3628345 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3937. Min Act: -0.1700
Data Index: 8772404 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3624. Min Act: -0.1700
Data Index: 8628475 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3781. Min Act: -0.1700
Data Index: 1742556 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3781. Min Act: -0.1700
Data Index: 6525869 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3624. Min Act: -0.1700
Data Index: 5529378 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3310. Min Act: -0.1700
Data Index: 1565967 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3310. Min Act: -0.1700
Data Index: 867256 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3153. Min Act: -0.1698
Data Index: 8628481 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.3153. Min Act: -0.1697
Data Index: 3628344 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.2839. Min Act: -0.1699
Data Index: 2328822 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.2839. Min Act: -0.1692
Data Index: 4807884 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.2525. Min Act: -0.1700
Data Index: 967017 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.2368. Min Act: -0.1700
Data Index: 1685206 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.2525. Min Act: -0.1700
Data Index: 2936305 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5661. Min Range: -3.5661
Max Act: 3.2368. Min Act: -0.1698
Data Index: 6525867 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19