Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4605 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0817. Min Range: -4.0817
Max Act: 4.0817. Min Act: -0.1700
Data Index: 2566153 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0817. Min Range: -4.0817
Max Act: 4.0817. Min Act: -0.1700
Data Index: 530488 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.9254. Min Act: -0.1700
Data Index: 8636244 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.9566. Min Act: -0.1700
Data Index: 8055925 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.9254. Min Act: -0.1700
Data Index: 977127 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8941. Min Act: -0.1700
Data Index: 3188668 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8628. Min Act: -0.1700
Data Index: 7484008 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8628. Min Act: -0.1700
Data Index: 4671162 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8628. Min Act: -0.1700
Data Index: 4802791 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8628. Min Act: -0.1700
Data Index: 4975962 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8628. Min Act: -0.1700
Data Index: 330874 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8628. Min Act: -0.1700
Data Index: 2923565 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8316. Min Act: -0.1700
Data Index: 5785967 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8628. Min Act: -0.1700
Data Index: 6747854 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8316. Min Act: -0.1700
Data Index: 1575797 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8316. Min Act: -0.1700
Data Index: 8697037 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8316. Min Act: -0.1700
Data Index: 2020749 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8316. Min Act: -0.1700
Data Index: 6203689 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8003. Min Act: -0.1700
Data Index: 196503 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0817. Min Range: -4.0817
Max Act: 3.8316. Min Act: -0.1700
Data Index: 4176037 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19