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

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

Neuron 1192 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: 0.0498. Min Range: -0.0498

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1513214 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1628331 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1605328 (Python Code)

Max Activating Token Index: 959

Text #3

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0445. Min Act: -0.0004

Data Index: 774976 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1423813 (Python Code)

Max Activating Token Index: 853

Text #5

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1406421 (Python Code)

Max Activating Token Index: 951

Text #6

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0442. Min Act: -0.0003

Data Index: 54206 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1414056 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0408. Min Act: -0.0003

Data Index: 543204 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0414. Min Act: -0.0003

Data Index: 706071 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1093374 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1646427 (Python Code)

Max Activating Token Index: 926

Text #12

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1364411 (Python Code)

Max Activating Token Index: 880

Text #13

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1363681 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1544770 (Python Code)

Max Activating Token Index: 434

Text #15

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1401658 (Python Code)

Max Activating Token Index: 996

Text #16

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0385. Min Act: -0.0003

Data Index: 556066 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1388990 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1575041 (Python Code)

Max Activating Token Index: 668

Text #19

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0380. Min Act: -0.0003

Data Index: 727967 (C4 (Web Text))

Max Activating Token Index: 177