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

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

Neuron 3944 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4870. Min Range: -5.4870

Max Act: 5.4870. Min Act: -0.0001

Data Index: 1121694 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 5.4870. Min Range: -5.4870

Max Act: 5.2581. Min Act: -0.0001

Data Index: 315108 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 5.4870. Min Range: -5.4870

Max Act: 5.4292. Min Act: -0.0001

Data Index: 502683 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.8977. Min Act: -0.0001

Data Index: 859147 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 5.4870. Min Range: -5.4870

Max Act: 5.0418. Min Act: -0.0001

Data Index: 993982 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.8152. Min Act: -0.0001

Data Index: 973090 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.5908. Min Act: -0.0001

Data Index: 1075764 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.1611. Min Act: -0.0001

Data Index: 200331 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.4717. Min Act: -0.0001

Data Index: 519379 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.5256. Min Act: -0.0001

Data Index: 868081 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.6409. Min Act: -0.0000

Data Index: 512739 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.2957. Min Act: -0.0001

Data Index: 64198 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.2727. Min Act: -0.0001

Data Index: 134004 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.2204. Min Act: -0.0001

Data Index: 1260371 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.3382. Min Act: -0.0001

Data Index: 1051003 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.3211. Min Act: -0.0001

Data Index: 509178 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.1545. Min Act: -0.0001

Data Index: 728837 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.1464. Min Act: -0.0001

Data Index: 300002 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.0622. Min Act: -0.0001

Data Index: 933704 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 5.4870. Min Range: -5.4870

Max Act: 4.3385. Min Act: -0.0001

Data Index: 1075441 (C4 (Web Text))

Max Activating Token Index: 737