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

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

Neuron 5042 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1829. Min Act: -0.0003

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0700. Min Act: -0.0003

Data Index: 337068 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0628. Min Act: -0.0002

Data Index: 239314 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1050372 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0517. Min Act: -0.0003

Data Index: 55012 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0492. Min Act: -0.0003

Data Index: 927432 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0515. Min Act: -0.0003

Data Index: 677311 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0516. Min Act: -0.0002

Data Index: 270429 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0485. Min Act: -0.0003

Data Index: 727297 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0480. Min Act: -0.0003

Data Index: 253459 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0474. Min Act: -0.0003

Data Index: 396339 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0469. Min Act: -0.0003

Data Index: 365920 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0461. Min Act: -0.0003

Data Index: 202461 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0440. Min Act: -0.0003

Data Index: 805284 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0453. Min Act: -0.0003

Data Index: 465339 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0428. Min Act: -0.0002

Data Index: 606654 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0453. Min Act: -0.0003

Data Index: 113992 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0445. Min Act: -0.0003

Data Index: 113258 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0424. Min Act: -0.0003

Data Index: 301096 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.0436. Min Act: -0.0003

Data Index: 79686 (C4 (Web Text))

Max Activating Token Index: 536