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

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

Neuron 4077 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4494. Min Act: -0.0001

Data Index: 1266771 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4324. Min Act: -0.0000

Data Index: 971587 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1275655 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4378. Min Act: -0.0001

Data Index: 729985 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3854. Min Act: -0.0001

Data Index: 381639 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3547. Min Act: -0.0000

Data Index: 997453 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3597. Min Act: -0.0000

Data Index: 393152 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1098101 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3266. Min Act: -0.0000

Data Index: 535419 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3409. Min Act: -0.0000

Data Index: 240677 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3371. Min Act: -0.0000

Data Index: 894655 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3359. Min Act: -0.0000

Data Index: 548481 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3314. Min Act: -0.0000

Data Index: 581716 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3748. Min Act: -0.0000

Data Index: 234425 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3475. Min Act: -0.0000

Data Index: 120308 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3369. Min Act: -0.0000

Data Index: 782559 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3149. Min Act: -0.0000

Data Index: 828544 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3316. Min Act: -0.0000

Data Index: 723627 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3269. Min Act: -0.0000

Data Index: 661536 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3322. Min Act: -0.0000

Data Index: 732087 (C4 (Web Text))

Max Activating Token Index: 829