Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2299 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.7512. Min Act: -0.1700
Data Index: 4876563 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.7512. Min Act: -0.1700
Data Index: 4926117 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.6730. Min Act: -0.1700
Data Index: 8378857 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.6730. Min Act: -0.1700
Data Index: 7939490 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.6574. Min Act: -0.1700
Data Index: 2334083 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.6574. Min Act: -0.1700
Data Index: 2074505 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.6261. Min Act: -0.1700
Data Index: 4171768 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.6104. Min Act: -0.1700
Data Index: 446510 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.6104. Min Act: -0.1700
Data Index: 6639855 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.6104. Min Act: -0.1700
Data Index: 3800152 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.6104. Min Act: -0.1700
Data Index: 1352394 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.5948. Min Act: -0.1700
Data Index: 1086142 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.5791. Min Act: -0.1700
Data Index: 1229109 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.5791. Min Act: -0.1700
Data Index: 1445529 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.5791. Min Act: -0.1700
Data Index: 6310079 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.5635. Min Act: -0.1700
Data Index: 6437938 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.5478. Min Act: -0.1700
Data Index: 838367 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.5478. Min Act: -0.1700
Data Index: 4876209 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.5478. Min Act: -0.1700
Data Index: 7126947 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7512. Min Range: -3.7512
Max Act: 3.5635. Min Act: -0.1700
Data Index: 1101584 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19