Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2310 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.5155. Min Act: -0.1700
Data Index: 7183075 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.4843. Min Act: -0.1700
Data Index: 4658626 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.4218. Min Act: -0.1700
Data Index: 4250535 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.4530. Min Act: -0.1700
Data Index: 3634654 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.3280. Min Act: -0.1700
Data Index: 5669275 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.2655. Min Act: -0.1700
Data Index: 5425178 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.2655. Min Act: -0.1700
Data Index: 1766564 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.2343. Min Act: -0.1700
Data Index: 505323 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.2655. Min Act: -0.1700
Data Index: 5786885 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.2343. Min Act: -0.1700
Data Index: 5934541 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.2343. Min Act: -0.1700
Data Index: 1451386 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.2343. Min Act: -0.1700
Data Index: 8194470 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.2030. Min Act: -0.1700
Data Index: 1766565 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.1405. Min Act: -0.1700
Data Index: 5645514 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.1718. Min Act: -0.1700
Data Index: 7954140 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.1718. Min Act: -0.1700
Data Index: 5316031 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.1405. Min Act: -0.1700
Data Index: 5948557 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.1405. Min Act: -0.1700
Data Index: 7997698 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.1405. Min Act: -0.1700
Data Index: 6597466 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5155. Min Range: -4.5155
Max Act: 4.1093. Min Act: -0.1700
Data Index: 6316367 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19