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

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

Neuron 4563 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.9172. Min Act: -0.0000

Data Index: 537409 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.7510. Min Act: -0.0000

Data Index: 383621 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.7239. Min Act: -0.0000

Data Index: 154499 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.6702. Min Act: -0.0000

Data Index: 913014 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.5715. Min Act: -0.0000

Data Index: 122649 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.4762. Min Act: -0.0000

Data Index: 16705 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.5949. Min Act: -0.0000

Data Index: 490097 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.4366. Min Act: -0.0000

Data Index: 245476 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.4105. Min Act: -0.0000

Data Index: 1195276 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.4153. Min Act: -0.0000

Data Index: 1063210 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.2466. Min Act: -0.0000

Data Index: 290254 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.4587. Min Act: -0.0000

Data Index: 1130434 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.2880. Min Act: -0.0000

Data Index: 857480 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.2933. Min Act: -0.0000

Data Index: 1069167 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.1696. Min Act: -0.0000

Data Index: 208742 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.1544. Min Act: -0.0000

Data Index: 869712 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.2338. Min Act: -0.0000

Data Index: 432764 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.1964. Min Act: -0.0000

Data Index: 1194417 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.0930. Min Act: -0.0000

Data Index: 258643 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 2.9172. Min Range: -2.9172

Max Act: 2.2484. Min Act: -0.0000

Data Index: 275355 (C4 (Web Text))

Max Activating Token Index: 947