Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2390 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2357. Min Range: -1.2357

Max Act: 1.2357. Min Act: -0.0000

Data Index: 670405 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1142435 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7993. Min Act: -0.0000

Data Index: 4847 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7889. Min Act: -0.0000

Data Index: 385983 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8428. Min Act: -0.0000

Data Index: 617054 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8373. Min Act: -0.0000

Data Index: 196946 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7732. Min Act: -0.0000

Data Index: 29537 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7581. Min Act: -0.0000

Data Index: 306182 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.6672. Min Act: -0.0000

Data Index: 64525 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7579. Min Act: -0.0000

Data Index: 789075 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7311. Min Act: -0.0000

Data Index: 467862 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7350. Min Act: -0.0000

Data Index: 118555 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7281. Min Act: -0.0000

Data Index: 193157 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7410. Min Act: -0.0000

Data Index: 336241 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7625. Min Act: -0.0000

Data Index: 268585 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.6830. Min Act: -0.0000

Data Index: 182513 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1313018 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1047263 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.6661. Min Act: -0.0000

Data Index: 242179 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7090. Min Act: -0.0000

Data Index: 83583 (C4 (Web Text))

Max Activating Token Index: 583