Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.6553. Min Act: -0.1700
Data Index: 2294156 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.6241. Min Act: -0.1700
Data Index: 470788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.5928. Min Act: -0.1700
Data Index: 6844939 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.5303. Min Act: -0.1700
Data Index: 4792158 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.5303. Min Act: -0.1700
Data Index: 1918533 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.5303. Min Act: -0.1700
Data Index: 4376208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.4678. Min Act: -0.1700
Data Index: 4264574 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.4678. Min Act: -0.1700
Data Index: 1151995 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.4678. Min Act: -0.1700
Data Index: 296366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.4678. Min Act: -0.1700
Data Index: 1001497 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.4678. Min Act: -0.1700
Data Index: 7422032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.4678. Min Act: -0.1700
Data Index: 5635702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.4366. Min Act: -0.1700
Data Index: 2318317 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.3741. Min Act: -0.1700
Data Index: 1986219 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.3741. Min Act: -0.1700
Data Index: 6540805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.3741. Min Act: -0.1700
Data Index: 2640316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.3741. Min Act: -0.1700
Data Index: 4488177 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.3741. Min Act: -0.1700
Data Index: 4792137 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.4053. Min Act: -0.1700
Data Index: 2412165 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6553. Min Range: -4.6553
Max Act: 4.3741. Min Act: -0.1700
Data Index: 7074913 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19