Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1035 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.6205. Min Act: -0.1700
Data Index: 4511479 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.5579. Min Act: -0.1700
Data Index: 5048732 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.5266. Min Act: -0.1700
Data Index: 4275631 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.5266. Min Act: -0.1700
Data Index: 2572356 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.5266. Min Act: -0.1700
Data Index: 2932302 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4953. Min Act: -0.1700
Data Index: 4953449 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4953. Min Act: -0.1700
Data Index: 7665872 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4953. Min Act: -0.1700
Data Index: 7909363 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4953. Min Act: -0.1700
Data Index: 2367479 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4639. Min Act: -0.1700
Data Index: 7943920 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4953. Min Act: -0.1700
Data Index: 8074143 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4953. Min Act: -0.1700
Data Index: 5999917 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4953. Min Act: -0.1700
Data Index: 3707684 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4953. Min Act: -0.1700
Data Index: 3858276 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4639. Min Act: -0.1700
Data Index: 2144826 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4639. Min Act: -0.1700
Data Index: 4123112 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4639. Min Act: -0.1700
Data Index: 5413185 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4639. Min Act: -0.1700
Data Index: 1167049 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4639. Min Act: -0.1700
Data Index: 3371357 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6205. Min Range: -3.6205
Max Act: 3.4639. Min Act: -0.1700
Data Index: 1655389 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19