Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5391 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: -0.0002

Data Index: 103497 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0436. Min Act: -0.0002

Data Index: 895394 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0473. Min Act: -0.0001

Data Index: 609489 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0465. Min Act: -0.0001

Data Index: 918609 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0451. Min Act: -0.0001

Data Index: 138194 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0459. Min Act: -0.0001

Data Index: 135391 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0430. Min Act: -0.0001

Data Index: 927348 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1053475 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0476. Min Act: -0.0001

Data Index: 95836 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0472. Min Act: -0.0001

Data Index: 543072 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1250219 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0423. Min Act: -0.0001

Data Index: 344411 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0407. Min Act: -0.0001

Data Index: 561554 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0404. Min Act: -0.0001

Data Index: 213915 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1308470 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0417. Min Act: -0.0001

Data Index: 763836 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0362. Min Act: -0.0001

Data Index: 264648 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0416. Min Act: -0.0001

Data Index: 135037 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0404. Min Act: -0.0001

Data Index: 222352 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0398. Min Act: -0.0001

Data Index: 977524 (C4 (Web Text))

Max Activating Token Index: 560