Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 76 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.8328. Min Act: -0.1700
Data Index: 70427 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.5828. Min Act: -0.1700
Data Index: 5193571 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.5203. Min Act: -0.1700
Data Index: 3370592 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.4890. Min Act: -0.1700
Data Index: 7204916 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.4890. Min Act: -0.1700
Data Index: 5696141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.4890. Min Act: -0.1700
Data Index: 2120895 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.4890. Min Act: -0.1700
Data Index: 4956170 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.4578. Min Act: -0.1700
Data Index: 4560788 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.4265. Min Act: -0.1700
Data Index: 8470116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.4265. Min Act: -0.1700
Data Index: 4711828 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.3953. Min Act: -0.1700
Data Index: 8259581 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.3640. Min Act: -0.1700
Data Index: 2379670 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.3953. Min Act: -0.1700
Data Index: 5814000 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.3953. Min Act: -0.1700
Data Index: 7549634 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.3953. Min Act: -0.1700
Data Index: 2399278 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.3327. Min Act: -0.1700
Data Index: 5332749 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.3327. Min Act: -0.1700
Data Index: 1652231 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.2702. Min Act: -0.1700
Data Index: 4532100 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.2390. Min Act: -0.1700
Data Index: 5787343 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8328. Min Range: -4.8328
Max Act: 4.2702. Min Act: -0.1700
Data Index: 1088577 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19