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

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

Neuron 735 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.4464. Min Act: -0.0000

Data Index: 1087179 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1371082 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1494027 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.1427. Min Act: -0.0000

Data Index: 471234 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.1348. Min Act: -0.0000

Data Index: 1283340 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0862. Min Act: -0.0000

Data Index: 568142 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1350475 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0917. Min Act: -0.0000

Data Index: 1224711 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0249. Min Act: -0.0000

Data Index: 173557 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1398437 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0490. Min Act: -0.0000

Data Index: 542547 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1632678 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1488476 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1337068 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.9575. Min Act: -0.0000

Data Index: 779487 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.9278. Min Act: -0.0000

Data Index: 296946 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1563311 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.8798. Min Act: -0.0000

Data Index: 397391 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0010. Min Act: -0.0000

Data Index: 931107 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1013844 (C4 (Web Text))

Max Activating Token Index: 266