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

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

Neuron 240 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: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0002

Data Index: 638802 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1291198 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1180875 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0573. Min Act: -0.0002

Data Index: 664178 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1202488 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0602. Min Act: -0.0001

Data Index: 457622 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1237599 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1118499 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1279921 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0554. Min Act: -0.0002

Data Index: 744675 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0554. Min Act: -0.0002

Data Index: 865212 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0548. Min Act: -0.0002

Data Index: 438763 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0536. Min Act: -0.0002

Data Index: 852825 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0528. Min Act: -0.0002

Data Index: 122058 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0521. Min Act: -0.0001

Data Index: 659117 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0520. Min Act: -0.0001

Data Index: 9832 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1224451 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0528. Min Act: -0.0002

Data Index: 239278 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1192943 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0515. Min Act: -0.0002

Data Index: 407473 (C4 (Web Text))

Max Activating Token Index: 378