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

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

Neuron 330 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2427. Min Range: -2.2427

Max Act: 2.2427. Min Act: -0.0000

Data Index: 1066541 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.5617. Min Act: -0.0000

Data Index: 80422 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.6550. Min Act: -0.0000

Data Index: 303574 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.5614. Min Act: -0.0000

Data Index: 904595 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.3651. Min Act: -0.0000

Data Index: 415452 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.2185. Min Act: -0.0000

Data Index: 1141974 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1569107 (Python Code)

Max Activating Token Index: 923

Text #7

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.3298. Min Act: -0.0000

Data Index: 901270 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.2855. Min Act: -0.0000

Data Index: 402917 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1096323 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.3141. Min Act: -0.0000

Data Index: 943812 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.2766. Min Act: -0.0000

Data Index: 808910 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.1118. Min Act: -0.0000

Data Index: 855761 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.1487. Min Act: -0.0000

Data Index: 833317 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1150290 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.2003. Min Act: -0.0000

Data Index: 225010 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.2392. Min Act: -0.0000

Data Index: 986639 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.0530. Min Act: -0.0000

Data Index: 569933 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 2.2427. Min Range: -2.2427

Max Act: 0.9803. Min Act: -0.0000

Data Index: 716721 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.0813. Min Act: -0.0000

Data Index: 56429 (C4 (Web Text))

Max Activating Token Index: 938