Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 99 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0465. Min Act: -0.0003

Data Index: 824688 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0424. Min Act: -0.0003

Data Index: 239793 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0432. Min Act: -0.0003

Data Index: 662676 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1540911 (Python Code)

Max Activating Token Index: 346

Text #4

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0410. Min Act: -0.0002

Data Index: 621319 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1017251 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0414. Min Act: -0.0003

Data Index: 673574 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0405. Min Act: -0.0003

Data Index: 860941 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0403. Min Act: -0.0004

Data Index: 1261769 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0393. Min Act: -0.0003

Data Index: 234213 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1069830 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0389. Min Act: -0.0003

Data Index: 432728 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0372. Min Act: -0.0004

Data Index: 1195723 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0374. Min Act: -0.0003

Data Index: 572187 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1185294 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1103911 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1166278 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1530713 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1230094 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1111276 (C4 (Web Text))

Max Activating Token Index: 95