Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1188. Min Range: -1.1188

Max Act: 1.1188. Min Act: -0.0000

Data Index: 704235 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.9228. Min Act: -0.0000

Data Index: 495393 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.9482. Min Act: -0.0000

Data Index: 984994 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.8796. Min Act: -0.0000

Data Index: 499140 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1291215 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.8385. Min Act: -0.0001

Data Index: 1190462 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.8284. Min Act: -0.0000

Data Index: 980783 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.8302. Min Act: -0.0000

Data Index: 708836 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7561. Min Act: -0.0001

Data Index: 1186690 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7701. Min Act: -0.0001

Data Index: 1011204 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7797. Min Act: -0.0000

Data Index: 500496 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.8027. Min Act: -0.0000

Data Index: 235582 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7922. Min Act: -0.0001

Data Index: 717892 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7675. Min Act: -0.0000

Data Index: 362547 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7341. Min Act: -0.0000

Data Index: 905973 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7530. Min Act: -0.0000

Data Index: 192708 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7660. Min Act: -0.0000

Data Index: 748779 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7246. Min Act: -0.0000

Data Index: 519378 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7015. Min Act: -0.0001

Data Index: 697081 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7049. Min Act: -0.0001

Data Index: 1326776 (C4 (Web Text))

Max Activating Token Index: 611