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

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

Neuron 950 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0005

Data Index: 521165 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0457. Min Act: -0.0005

Data Index: 797201 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0451. Min Act: -0.0005

Data Index: 890920 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0439. Min Act: -0.0005

Data Index: 111539 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0440. Min Act: -0.0005

Data Index: 519379 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0428. Min Act: -0.0004

Data Index: 965987 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0406. Min Act: -0.0005

Data Index: 516706 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0424. Min Act: -0.0005

Data Index: 1318870 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0408. Min Act: -0.0005

Data Index: 681308 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0396. Min Act: -0.0005

Data Index: 1288366 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0398. Min Act: -0.0005

Data Index: 792474 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0397. Min Act: -0.0005

Data Index: 1351280 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0390. Min Act: -0.0005

Data Index: 155566 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0403. Min Act: -0.0004

Data Index: 592713 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0420. Min Act: -0.0005

Data Index: 631555 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0414. Min Act: -0.0005

Data Index: 110095 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0384. Min Act: -0.0005

Data Index: 112199 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0383. Min Act: -0.0004

Data Index: 970134 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0393. Min Act: -0.0005

Data Index: 1069039 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1097029 (C4 (Web Text))

Max Activating Token Index: 668