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

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

Neuron 1567 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0005

Data Index: 872914 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0555. Min Act: -0.0005

Data Index: 486583 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0537. Min Act: -0.0005

Data Index: 517271 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0541. Min Act: -0.0005

Data Index: 1160574 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0531. Min Act: -0.0005

Data Index: 295811 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0516. Min Act: -0.0005

Data Index: 1289259 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0526. Min Act: -0.0005

Data Index: 1352008 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0523. Min Act: -0.0005

Data Index: 1025891 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0513. Min Act: -0.0005

Data Index: 169871 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0503. Min Act: -0.0005

Data Index: 941483 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0505. Min Act: -0.0005

Data Index: 639184 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0494. Min Act: -0.0005

Data Index: 934314 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0513. Min Act: -0.0005

Data Index: 496197 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0494. Min Act: -0.0005

Data Index: 277928 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0478. Min Act: -0.0005

Data Index: 47140 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0472. Min Act: -0.0005

Data Index: 1159598 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0468. Min Act: -0.0005

Data Index: 100463 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0474. Min Act: -0.0005

Data Index: 30578 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0467. Min Act: -0.0005

Data Index: 585734 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0470. Min Act: -0.0005

Data Index: 11074 (C4 (Web Text))

Max Activating Token Index: 579