Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 95 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0004

Data Index: 616812 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0406. Min Act: -0.0004

Data Index: 803648 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0448. Min Act: -0.0004

Data Index: 335708 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0398. Min Act: -0.0004

Data Index: 189359 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0432. Min Act: -0.0004

Data Index: 989885 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0421. Min Act: -0.0004

Data Index: 507797 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0383. Min Act: -0.0004

Data Index: 763602 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0446. Min Act: -0.0004

Data Index: 931579 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0391. Min Act: -0.0004

Data Index: 303691 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0384. Min Act: -0.0004

Data Index: 954085 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0441. Min Act: -0.0004

Data Index: 1010785 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0403. Min Act: -0.0004

Data Index: 284122 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0428. Min Act: -0.0004

Data Index: 389565 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0412. Min Act: -0.0004

Data Index: 274711 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0372. Min Act: -0.0004

Data Index: 971949 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1080483 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0405. Min Act: -0.0004

Data Index: 1169519 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0453. Min Act: -0.0004

Data Index: 84690 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0426. Min Act: -0.0004

Data Index: 933746 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0377. Min Act: -0.0004

Data Index: 909689 (C4 (Web Text))

Max Activating Token Index: 39