Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5060 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6548. Min Range: -3.6548

Max Act: 3.6548. Min Act: -0.0001

Data Index: 460300 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.9153. Min Act: -0.0001

Data Index: 746828 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 3.6548. Min Range: -3.6548

Max Act: 3.0521. Min Act: -0.0001

Data Index: 968288 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.6475. Min Act: -0.0001

Data Index: 562876 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.5918. Min Act: -0.0001

Data Index: 316549 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.6771. Min Act: -0.0001

Data Index: 881233 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.8143. Min Act: -0.0001

Data Index: 1154528 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.4941. Min Act: -0.0001

Data Index: 416006 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.6277. Min Act: -0.0001

Data Index: 453087 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.3789. Min Act: -0.0001

Data Index: 514664 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.4782. Min Act: -0.0001

Data Index: 755415 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.5444. Min Act: -0.0001

Data Index: 341363 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.7838. Min Act: -0.0001

Data Index: 1334479 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.4743. Min Act: -0.0001

Data Index: 1218367 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.5465. Min Act: -0.0001

Data Index: 737025 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.1521. Min Act: -0.0001

Data Index: 590014 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.2986. Min Act: -0.0001

Data Index: 327579 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.4039. Min Act: -0.0001

Data Index: 465784 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.2104. Min Act: -0.0001

Data Index: 837698 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 3.6548. Min Range: -3.6548

Max Act: 2.1385. Min Act: -0.0001

Data Index: 737257 (C4 (Web Text))

Max Activating Token Index: 172