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

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

Neuron 4156 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.5059. Min Act: -0.0000

Data Index: 1542636 (Python Code)

Max Activating Token Index: 558

Text #1

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0883. Min Act: -0.0000

Data Index: 360129 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1438726 (Python Code)

Max Activating Token Index: 548

Text #3

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1218966 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0993. Min Act: -0.0000

Data Index: 976831 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0497. Min Act: -0.0000

Data Index: 220751 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0441. Min Act: -0.0000

Data Index: 142828 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0401. Min Act: -0.0000

Data Index: 405793 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1350990 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1260377 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1071095 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1054302 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1401461 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9325. Min Act: -0.0000

Data Index: 588359 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1272645 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1381986 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9756. Min Act: -0.0000

Data Index: 751763 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.8472. Min Act: -0.0000

Data Index: 686057 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1302730 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.8848. Min Act: -0.0000

Data Index: 555615 (C4 (Web Text))

Max Activating Token Index: 529