Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1225 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0002

Data Index: 77641 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0581. Min Act: -0.0002

Data Index: 94843 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0595. Min Act: -0.0002

Data Index: 379299 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0588. Min Act: -0.0002

Data Index: 671236 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0535. Min Act: -0.0001

Data Index: 671578 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0524. Min Act: -0.0002

Data Index: 883061 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0524. Min Act: -0.0000

Data Index: 424172 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0518. Min Act: -0.0002

Data Index: 789874 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0506. Min Act: -0.0001

Data Index: 38184 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0500. Min Act: -0.0002

Data Index: 61369 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0506. Min Act: -0.0001

Data Index: 976455 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0495. Min Act: -0.0002

Data Index: 888533 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0494. Min Act: -0.0002

Data Index: 592934 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0483. Min Act: -0.0002

Data Index: 237855 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0480. Min Act: -0.0002

Data Index: 32321 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0475. Min Act: -0.0002

Data Index: 999570 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0467. Min Act: -0.0002

Data Index: 933837 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0451. Min Act: -0.0002

Data Index: 385790 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1141259 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0466. Min Act: -0.0002

Data Index: 531393 (C4 (Web Text))

Max Activating Token Index: 475