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

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

Neuron 22 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.4559. Min Act: -0.0000

Data Index: 383977 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.4719. Min Act: -0.0000

Data Index: 166129 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.4038. Min Act: -0.0000

Data Index: 555233 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1027506 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3332. Min Act: -0.0000

Data Index: 306365 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1325681 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3848. Min Act: -0.0000

Data Index: 421537 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1055555 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3194. Min Act: -0.0000

Data Index: 652791 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3521. Min Act: -0.0000

Data Index: 764359 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3584. Min Act: -0.0000

Data Index: 715528 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.2948. Min Act: -0.0000

Data Index: 666420 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3392. Min Act: -0.0000

Data Index: 351675 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3293. Min Act: -0.0000

Data Index: 533422 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1354084 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.2875. Min Act: -0.0000

Data Index: 493472 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3160. Min Act: -0.0000

Data Index: 101314 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1061050 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3401. Min Act: -0.0000

Data Index: 254584 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1094726 (C4 (Web Text))

Max Activating Token Index: 178