Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3883 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.6954. Min Act: -0.1700
Data Index: 1300065 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.6016. Min Act: -0.1699
Data Index: 4448420 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.5704. Min Act: -0.1699
Data Index: 8637323 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.5079. Min Act: -0.1700
Data Index: 5568902 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4766. Min Act: -0.1700
Data Index: 642687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4766. Min Act: -0.1699
Data Index: 4912291 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4454. Min Act: -0.1699
Data Index: 930752 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4454. Min Act: -0.1700
Data Index: 8449721 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4454. Min Act: -0.1699
Data Index: 6174533 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4454. Min Act: -0.1700
Data Index: 5593321 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4454. Min Act: -0.1700
Data Index: 2097865 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4454. Min Act: -0.1700
Data Index: 2832759 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4141. Min Act: -0.1700
Data Index: 3459748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4141. Min Act: -0.1699
Data Index: 1671321 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4141. Min Act: -0.1700
Data Index: 2062259 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4141. Min Act: -0.1699
Data Index: 3484851 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3829. Min Act: -0.1700
Data Index: 3771232 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4141. Min Act: -0.1699
Data Index: 3915353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4141. Min Act: -0.1699
Data Index: 4217740 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4141. Min Act: -0.1700
Data Index: 4237232 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19