Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4411 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.7515. Min Act: -0.0000

Data Index: 634660 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1227235 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.5889. Min Act: -0.0000

Data Index: 634149 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.5019. Min Act: -0.0000

Data Index: 227414 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1215774 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4861. Min Act: 0.0000

Data Index: 1214478 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1112655 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4751. Min Act: -0.0000

Data Index: 984073 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4874. Min Act: -0.0000

Data Index: 738005 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1044357 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1231008 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4864. Min Act: -0.0000

Data Index: 272019 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4550. Min Act: -0.0000

Data Index: 647592 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4504. Min Act: -0.0000

Data Index: 977255 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1112868 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4454. Min Act: -0.0000

Data Index: 361659 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4429. Min Act: -0.0000

Data Index: 237700 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4448. Min Act: -0.0000

Data Index: 427048 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4363. Min Act: -0.0000

Data Index: 279753 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1255394 (C4 (Web Text))

Max Activating Token Index: 788