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

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

Neuron 155 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.8478. Min Act: -0.0001

Data Index: 635144 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.7506. Min Act: -0.0001

Data Index: 397343 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.5798. Min Act: -0.0002

Data Index: 1357802 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.7198. Min Act: -0.0002

Data Index: 973669 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.5924. Min Act: -0.0002

Data Index: 1332344 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.5208. Min Act: -0.0001

Data Index: 818854 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.5108. Min Act: -0.0001

Data Index: 1127138 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.5798. Min Act: -0.0001

Data Index: 398097 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.5161. Min Act: -0.0002

Data Index: 1268316 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.6116. Min Act: -0.0001

Data Index: 1166168 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.4845. Min Act: -0.0002

Data Index: 214806 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.5310. Min Act: -0.0001

Data Index: 956727 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.5174. Min Act: -0.0001

Data Index: 1249943 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.4770. Min Act: -0.0002

Data Index: 83929 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.4701. Min Act: -0.0002

Data Index: 53630 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.2218. Min Act: -0.0002

Data Index: 1221276 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.3417. Min Act: -0.0002

Data Index: 1160025 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.3967. Min Act: -0.0002

Data Index: 252895 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.4119. Min Act: -0.0001

Data Index: 1253153 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.8478. Min Range: -1.8478

Max Act: 1.3202. Min Act: -0.0001

Data Index: 430743 (C4 (Web Text))

Max Activating Token Index: 803