Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 12 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1951. Min Act: -0.0000

Data Index: 747151 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1497. Min Act: -0.0000

Data Index: 597236 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1441. Min Act: -0.0000

Data Index: 897635 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1336170 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1297. Min Act: -0.0000

Data Index: 15963 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1434. Min Act: -0.0000

Data Index: 70112 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1060696 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1231. Min Act: -0.0000

Data Index: 906545 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1348. Min Act: -0.0000

Data Index: 870026 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1175. Min Act: -0.0001

Data Index: 384306 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1280. Min Act: -0.0001

Data Index: 624477 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1322947 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1211672 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1209. Min Act: -0.0000

Data Index: 718558 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1188. Min Act: -0.0000

Data Index: 833999 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1222990 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1177. Min Act: -0.0001

Data Index: 907160 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1171951 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1263. Min Act: -0.0000

Data Index: 547946 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1170. Min Act: -0.0000

Data Index: 858356 (C4 (Web Text))

Max Activating Token Index: 967