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

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

Neuron 716 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.9461. Min Act: -0.0001

Data Index: 429758 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.6685. Min Act: -0.0000

Data Index: 325942 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.6147. Min Act: -0.0000

Data Index: 143730 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.5574. Min Act: -0.0000

Data Index: 485661 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.5049. Min Act: -0.0000

Data Index: 715108 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.5190. Min Act: -0.0000

Data Index: 908309 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4749. Min Act: -0.0000

Data Index: 894257 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4596. Min Act: -0.0000

Data Index: 640794 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4791. Min Act: -0.0000

Data Index: 824201 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4861. Min Act: -0.0000

Data Index: 795134 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4339. Min Act: -0.0000

Data Index: 145856 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4303. Min Act: -0.0000

Data Index: 844445 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4508. Min Act: -0.0000

Data Index: 656142 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4644. Min Act: -0.0000

Data Index: 270976 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4397. Min Act: -0.0000

Data Index: 91282 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1319585 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4279. Min Act: -0.0000

Data Index: 153210 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4810. Min Act: -0.0000

Data Index: 622736 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1204475 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.4084. Min Act: -0.0000

Data Index: 883586 (C4 (Web Text))

Max Activating Token Index: 585