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

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

Neuron 131 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: 0.4499. Min Range: -0.4499

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1055217 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4221. Min Act: -0.0001

Data Index: 843194 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4331. Min Act: -0.0001

Data Index: 948571 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4187. Min Act: -0.0001

Data Index: 1240779 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4176. Min Act: -0.0001

Data Index: 443421 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4256. Min Act: -0.0001

Data Index: 325915 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.3887. Min Act: -0.0001

Data Index: 666896 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4309. Min Act: -0.0001

Data Index: 644716 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4499. Min Act: -0.0001

Data Index: 979892 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.3985. Min Act: -0.0001

Data Index: 129459 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1314814 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.3851. Min Act: -0.0001

Data Index: 1120378 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.3966. Min Act: -0.0000

Data Index: 735599 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.3989. Min Act: -0.0001

Data Index: 862094 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4088. Min Act: -0.0001

Data Index: 399094 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.3943. Min Act: -0.0000

Data Index: 871477 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.3906. Min Act: -0.0000

Data Index: 436281 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1356787 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.3984. Min Act: -0.0001

Data Index: 155575 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.4499. Min Range: -0.4499

Max Act: 0.3846. Min Act: -0.0000

Data Index: 486198 (C4 (Web Text))

Max Activating Token Index: 928