Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4298 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.6256. Min Act: -0.1700
Data Index: 3209657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4691. Min Act: -0.1700
Data Index: 2410739 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.5004. Min Act: -0.1700
Data Index: 4324395 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4691. Min Act: -0.1700
Data Index: 5309925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4377. Min Act: -0.1700
Data Index: 5240076 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4377. Min Act: -0.1700
Data Index: 3543185 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4377. Min Act: -0.1700
Data Index: 1190324 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4377. Min Act: -0.1700
Data Index: 4633343 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4377. Min Act: -0.1700
Data Index: 7553290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4377. Min Act: -0.1700
Data Index: 3167516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4064. Min Act: -0.1700
Data Index: 6313123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4064. Min Act: -0.1700
Data Index: 7692143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4064. Min Act: -0.1700
Data Index: 7733756 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4064. Min Act: -0.1700
Data Index: 3121323 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4064. Min Act: -0.1700
Data Index: 3781386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4064. Min Act: -0.1700
Data Index: 3524206 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.4064. Min Act: -0.1700
Data Index: 3017898 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.3750. Min Act: -0.1700
Data Index: 3170162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.3750. Min Act: -0.1700
Data Index: 1129855 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6256. Min Range: -3.6256
Max Act: 3.3750. Min Act: -0.1700
Data Index: 404946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19