Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.5948. Min Act: -0.1700
Data Index: 8524361 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.5482. Min Act: -0.1700
Data Index: 1546370 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.5482. Min Act: -0.1700
Data Index: 2904482 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.5252. Min Act: -0.1700
Data Index: 4790255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.5329. Min Act: -0.1697
Data Index: 7261576 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.5252. Min Act: -0.1699
Data Index: 4432398 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4876. Min Act: -0.1698
Data Index: 2177885 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4876. Min Act: -0.1700
Data Index: 2064618 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4876. Min Act: -0.1700
Data Index: 8685226 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4653. Min Act: -0.1690
Data Index: 5701427 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4653. Min Act: -0.1700
Data Index: 7498470 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4653. Min Act: -0.1700
Data Index: 8120975 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4653. Min Act: -0.1700
Data Index: 4564454 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4653. Min Act: -0.1700
Data Index: 4235387 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4653. Min Act: -0.1696
Data Index: 2111990 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4653. Min Act: -0.1700
Data Index: 571305 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4653. Min Act: -0.1699
Data Index: 835137 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4361. Min Act: -0.1685
Data Index: 1125193 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4217. Min Act: -0.1700
Data Index: 171101 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5948. Min Range: -0.5948
Max Act: 0.4075. Min Act: -0.1687
Data Index: 6475718 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19