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

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

Neuron 85 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0002

Data Index: 42356 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0568. Min Act: -0.0002

Data Index: 395527 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0565. Min Act: -0.0002

Data Index: 879249 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0553. Min Act: -0.0002

Data Index: 365171 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0529. Min Act: -0.0002

Data Index: 365240 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1131434 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1080665 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0484. Min Act: -0.0002

Data Index: 770020 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1291647 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1145129 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1209945 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0441. Min Act: -0.0002

Data Index: 161271 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0412. Min Act: -0.0002

Data Index: 304401 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0393. Min Act: -0.0002

Data Index: 194894 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0397. Min Act: -0.0002

Data Index: 534486 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1227923 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1186219 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0316. Min Act: -0.0002

Data Index: 163128 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1529601 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0262. Min Act: -0.0002

Data Index: 729890 (C4 (Web Text))

Max Activating Token Index: 792