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

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

Neuron 1896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2589. Min Act: -0.0001

Data Index: 1317238 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2680. Min Act: -0.0001

Data Index: 937146 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2619. Min Act: -0.0001

Data Index: 367545 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2513. Min Act: -0.0001

Data Index: 547398 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2674. Min Act: -0.0000

Data Index: 215897 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2481. Min Act: -0.0001

Data Index: 872768 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1287574 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2363. Min Act: -0.0001

Data Index: 852901 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1189472 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1087675 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2416. Min Act: -0.0001

Data Index: 1174055 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2245. Min Act: -0.0001

Data Index: 976615 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2480. Min Act: -0.0001

Data Index: 866769 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2230. Min Act: -0.0001

Data Index: 276797 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2242. Min Act: -0.0001

Data Index: 660053 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2436. Min Act: -0.0001

Data Index: 1067727 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2459. Min Act: -0.0001

Data Index: 700490 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1260145 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2188. Min Act: -0.0001

Data Index: 409062 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 563