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

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

Neuron 833 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: 0.2702. Min Range: -0.2702

Max Act: 0.2691. Min Act: -0.0002

Data Index: 676611 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2645. Min Act: -0.0002

Data Index: 166027 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2702. Min Act: -0.0002

Data Index: 1086803 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2510. Min Act: -0.0002

Data Index: 134600 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2442. Min Act: -0.0002

Data Index: 419173 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2669. Min Act: -0.0002

Data Index: 279273 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2590. Min Act: -0.0002

Data Index: 966178 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2557. Min Act: -0.0002

Data Index: 1331007 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2465. Min Act: -0.0002

Data Index: 748838 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2459. Min Act: -0.0002

Data Index: 816312 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2434. Min Act: -0.0002

Data Index: 1166534 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2413. Min Act: -0.0002

Data Index: 657578 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2437. Min Act: -0.0002

Data Index: 964030 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2562. Min Act: -0.0002

Data Index: 102876 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2428. Min Act: -0.0002

Data Index: 746553 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2357. Min Act: -0.0002

Data Index: 382300 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2358. Min Act: -0.0002

Data Index: 984784 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2343. Min Act: -0.0002

Data Index: 698073 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2351. Min Act: -0.0002

Data Index: 160058 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2195. Min Act: -0.0002

Data Index: 632916 (C4 (Web Text))

Max Activating Token Index: 57