Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1156 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.5249. Min Act: -0.1697

Data Index: 1330058 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.5022. Min Act: -0.1700

Data Index: 720944 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.4775. Min Act: -0.1345

Data Index: 1461927 (Python Code)

Max Activating Token Index: 278

Text #3

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3909. Min Act: -0.1700

Data Index: 942673 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3811. Min Act: -0.1700

Data Index: 830355 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3890. Min Act: -0.1700

Data Index: 1504525 (Python Code)

Max Activating Token Index: 947

Text #6

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3817. Min Act: -0.1700

Data Index: 148418 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3863. Min Act: -0.1700

Data Index: 126714 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3712. Min Act: -0.1700

Data Index: 363910 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3803. Min Act: -0.1685

Data Index: 1216840 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3694. Min Act: -0.1697

Data Index: 875134 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3759. Min Act: -0.1660

Data Index: 1016531 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3635. Min Act: -0.1697

Data Index: 332319 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3658. Min Act: -0.1685

Data Index: 449624 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3659. Min Act: -0.1699

Data Index: 1489160 (Python Code)

Max Activating Token Index: 780

Text #15

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3484. Min Act: -0.1699

Data Index: 1601525 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3583. Min Act: -0.1700

Data Index: 820342 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3308. Min Act: -0.1525

Data Index: 1013328 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3410. Min Act: -0.1693

Data Index: 1313360 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 2.5249. Min Range: -2.5249

Max Act: 2.3393. Min Act: -0.1700

Data Index: 1378139 (Python Code)

Max Activating Token Index: 38