Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3881 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1700
Data Index: 4180356 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1700
Data Index: 287038 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1699
Data Index: 7312986 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1700
Data Index: 5240746 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1700
Data Index: 7004814 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1699
Data Index: 8252466 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1699
Data Index: 3725647 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1700
Data Index: 1260919 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1700
Data Index: 8790544 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1699
Data Index: 5989212 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1700
Data Index: 2846795 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1700
Data Index: 2750369 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1693
Data Index: 8774347 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.5218. Min Act: -0.1700
Data Index: 8423087 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.4917. Min Act: -0.1699
Data Index: 3496453 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.4842. Min Act: -0.1696
Data Index: 438263 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.4768. Min Act: -0.1700
Data Index: 5403436 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.4768. Min Act: -0.1695
Data Index: 5633956 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.4842. Min Act: -0.1699
Data Index: 386881 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5218. Min Range: -0.5218
Max Act: 0.4842. Min Act: -0.1700
Data Index: 5426241 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19