Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0001

Data Index: 279643 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0572. Min Act: -0.0001

Data Index: 140058 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0492. Min Act: -0.0001

Data Index: 890947 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0478. Min Act: -0.0001

Data Index: 212237 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1102263 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0470. Min Act: -0.0001

Data Index: 546294 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1112206 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1233275 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0433. Min Act: -0.0001

Data Index: 958037 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0423. Min Act: -0.0001

Data Index: 190097 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1111587 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0427. Min Act: -0.0001

Data Index: 413070 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1025345 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0435. Min Act: -0.0001

Data Index: 487360 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0418. Min Act: -0.0001

Data Index: 546981 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0403. Min Act: -0.0001

Data Index: 284017 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0428. Min Act: -0.0001

Data Index: 740597 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0390. Min Act: -0.0001

Data Index: 239976 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0405. Min Act: -0.0001

Data Index: 168565 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0434. Min Act: -0.0001

Data Index: 682400 (C4 (Web Text))

Max Activating Token Index: 844