Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0773. Min Act: -0.1700
Data Index: 5967038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0461. Min Act: -0.1700
Data Index: 5958811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9836. Min Act: -0.1700
Data Index: 1398975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0148. Min Act: -0.1700
Data Index: 3344368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0148. Min Act: -0.1700
Data Index: 5689019 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0148. Min Act: -0.1700
Data Index: 2942860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0148. Min Act: -0.1700
Data Index: 6952971 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9836. Min Act: -0.1700
Data Index: 2614077 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0148. Min Act: -0.1700
Data Index: 237769 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0148. Min Act: -0.1699
Data Index: 6250712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9836. Min Act: -0.1700
Data Index: 4761752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9836. Min Act: -0.1700
Data Index: 1094397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9836. Min Act: -0.1700
Data Index: 5510650 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0148. Min Act: -0.1700
Data Index: 3229729 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9836. Min Act: -0.1700
Data Index: 6054965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9523. Min Act: -0.1698
Data Index: 3469606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9523. Min Act: -0.1700
Data Index: 6345958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9523. Min Act: -0.1700
Data Index: 3964355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9210. Min Act: -0.1700
Data Index: 3165169 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9210. Min Act: -0.1700
Data Index: 1841373 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19