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

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

Neuron 1270 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: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0002

Data Index: 137529 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0002

Data Index: 940580 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0441. Min Act: -0.0002

Data Index: 660116 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0426. Min Act: -0.0001

Data Index: 714431 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1441484 (Python Code)

Max Activating Token Index: 520

Text #5

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0413. Min Act: -0.0002

Data Index: 209824 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1609588 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0387. Min Act: -0.0002

Data Index: 345606 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1166966 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1228918 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1572988 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0390. Min Act: -0.0001

Data Index: 176566 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1583065 (Python Code)

Max Activating Token Index: 913

Text #13

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0385. Min Act: -0.0002

Data Index: 828330 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0388. Min Act: -0.0002

Data Index: 538687 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0394. Min Act: -0.0002

Data Index: 778726 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0400. Min Act: -0.0002

Data Index: 988760 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0393. Min Act: -0.0002

Data Index: 732477 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0392. Min Act: -0.0002

Data Index: 777024 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0401. Min Act: -0.0002

Data Index: 746522 (C4 (Web Text))

Max Activating Token Index: 988