Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4148 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0000

Data Index: 781198 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0566. Min Act: -0.0000

Data Index: 280224 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0495. Min Act: -0.0000

Data Index: 840183 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0430. Min Act: -0.0000

Data Index: 1389939 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0453. Min Act: -0.0000

Data Index: 742568 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0436. Min Act: -0.0000

Data Index: 698180 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0397. Min Act: -0.0000

Data Index: 952636 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1380868 (Python Code)

Max Activating Token Index: 962

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0382. Min Act: -0.0000

Data Index: 871109 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1389630 (Python Code)

Max Activating Token Index: 927

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1290505 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0417. Min Act: -0.0000

Data Index: 171391 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0429. Min Act: -0.0000

Data Index: 295837 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0393. Min Act: -0.0000

Data Index: 465012 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0407. Min Act: -0.0000

Data Index: 843206 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1004998 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0292. Min Act: -0.0000

Data Index: 15595 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0383. Min Act: -0.0000

Data Index: 625168 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0345. Min Act: -0.0000

Data Index: 589600 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0412. Min Act: -0.0000

Data Index: 119830 (C4 (Web Text))

Max Activating Token Index: 24