Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4749 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.8354. Min Act: -0.1700
Data Index: 404456 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.8036. Min Act: -0.1700
Data Index: 8647811 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7557. Min Act: -0.1700
Data Index: 5906205 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7717. Min Act: -0.1700
Data Index: 5013657 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7557. Min Act: -0.1700
Data Index: 5245491 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7398. Min Act: -0.1700
Data Index: 8124130 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7398. Min Act: -0.1700
Data Index: 3109264 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7398. Min Act: -0.1700
Data Index: 2376288 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7398. Min Act: -0.1700
Data Index: 8680203 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7398. Min Act: -0.1700
Data Index: 2677144 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7238. Min Act: -0.1700
Data Index: 4037738 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7238. Min Act: -0.1700
Data Index: 6312392 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7238. Min Act: -0.1700
Data Index: 2625268 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7238. Min Act: -0.1700
Data Index: 8341335 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7078. Min Act: -0.1700
Data Index: 3844972 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7078. Min Act: -0.1700
Data Index: 1819922 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7238. Min Act: -0.1700
Data Index: 2708666 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7078. Min Act: -0.1700
Data Index: 606482 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7078. Min Act: -0.1700
Data Index: 346651 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8354. Min Range: -2.8354
Max Act: 2.7078. Min Act: -0.1700
Data Index: 4564803 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19