Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 398 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.5377. Min Act: -0.1700
Data Index: 3720780 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.5064. Min Act: -0.1700
Data Index: 6214654 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 6173447 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4439. Min Act: -0.1700
Data Index: 3333993 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 7604277 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 8517195 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 7735239 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 6104263 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 443728 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 6060246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 2236345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 4405830 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 1657301 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 6220999 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 532765 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 6047351 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 5509951 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 5502080 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 5339835 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5377. Min Range: -4.5377
Max Act: 4.4126. Min Act: -0.1700
Data Index: 295599 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19