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

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

Neuron 3713 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1114916 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1722. Min Act: -0.0000

Data Index: 579512 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1110636 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1585. Min Act: -0.0000

Data Index: 267814 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1033259 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1457. Min Act: -0.0000

Data Index: 721245 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1301157 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1308. Min Act: -0.0000

Data Index: 926566 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1248. Min Act: -0.0000

Data Index: 862997 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1285. Min Act: -0.0000

Data Index: 723785 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1243. Min Act: -0.0000

Data Index: 87204 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1243. Min Act: -0.0000

Data Index: 767454 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1274. Min Act: -0.0000

Data Index: 639507 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1257224 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1295. Min Act: -0.0000

Data Index: 475588 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1120. Min Act: -0.0000

Data Index: 487525 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1240. Min Act: -0.0000

Data Index: 408222 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1146. Min Act: -0.0000

Data Index: 383858 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.1137. Min Act: -0.0000

Data Index: 206297 (C4 (Web Text))

Max Activating Token Index: 613