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

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

Neuron 232 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1644. Min Range: -1.1644

Max Act: 1.1444. Min Act: -0.0000

Data Index: 356637 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 1.1644. Min Range: -1.1644

Max Act: 1.1644. Min Act: -0.0000

Data Index: 316919 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 1.1644. Min Range: -1.1644

Max Act: 1.0474. Min Act: -0.0000

Data Index: 368760 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 1.1644. Min Range: -1.1644

Max Act: 1.0336. Min Act: -0.0000

Data Index: 368159 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.9748. Min Act: -0.0000

Data Index: 318614 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.9156. Min Act: -0.0000

Data Index: 585989 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.9638. Min Act: -0.0000

Data Index: 546918 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1010572 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.9460. Min Act: -0.0001

Data Index: 909026 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.9166. Min Act: -0.0000

Data Index: 897719 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.8838. Min Act: -0.0000

Data Index: 464623 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.9018. Min Act: -0.0000

Data Index: 354434 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.8913. Min Act: -0.0000

Data Index: 366525 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.8628. Min Act: -0.0000

Data Index: 65332 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1193337 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.8989. Min Act: -0.0000

Data Index: 411457 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1348657 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.8513. Min Act: -0.0000

Data Index: 73071 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1235767 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.8464. Min Act: -0.0000

Data Index: 320140 (C4 (Web Text))

Max Activating Token Index: 634