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

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

Neuron 1227 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: 1.4063. Min Range: -1.4063

Max Act: 1.4063. Min Act: -0.0001

Data Index: 45461 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.3163. Min Act: -0.0001

Data Index: 212395 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.1401. Min Act: -0.0001

Data Index: 97917 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.3173. Min Act: -0.0001

Data Index: 725114 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.2441. Min Act: -0.0001

Data Index: 740154 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.2352. Min Act: -0.0000

Data Index: 775088 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.3249. Min Act: -0.0001

Data Index: 734201 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.1937. Min Act: -0.0001

Data Index: 364714 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.1390. Min Act: -0.0001

Data Index: 286094 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.2240. Min Act: -0.0001

Data Index: 129130 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.2455. Min Act: -0.0001

Data Index: 228015 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.2361. Min Act: -0.0001

Data Index: 298805 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.2503. Min Act: -0.0001

Data Index: 558084 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.2965. Min Act: -0.0001

Data Index: 397221 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.1596. Min Act: -0.0001

Data Index: 1318637 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.1795. Min Act: -0.0001

Data Index: 446467 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.1441. Min Act: -0.0001

Data Index: 975430 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.1367. Min Act: -0.0001

Data Index: 1218592 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.2018. Min Act: -0.0001

Data Index: 538768 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.4063. Min Range: -1.4063

Max Act: 1.1315. Min Act: -0.0001

Data Index: 1095846 (C4 (Web Text))

Max Activating Token Index: 972