Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3820 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0572. Min Act: -0.0001

Data Index: 514574 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0447. Min Act: -0.0001

Data Index: 242439 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1039423 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0511. Min Act: -0.0001

Data Index: 864946 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0437. Min Act: -0.0001

Data Index: 295103 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0480. Min Act: -0.0001

Data Index: 973526 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0493. Min Act: -0.0001

Data Index: 1041858 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0402. Min Act: -0.0001

Data Index: 5210 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0394. Min Act: -0.0001

Data Index: 722737 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0392. Min Act: -0.0001

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0400. Min Act: -0.0001

Data Index: 239948 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0348. Min Act: -0.0001

Data Index: 169216 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0327. Min Act: -0.0001

Data Index: 453442 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0361. Min Act: -0.0001

Data Index: 476386 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0307. Min Act: -0.0001

Data Index: 877930 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0258. Min Act: -0.0001

Data Index: 224794 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1199573 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1164148 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0294. Min Act: -0.0001

Data Index: 1057316 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0241. Min Act: -0.0001

Data Index: 377485 (C4 (Web Text))

Max Activating Token Index: 95