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

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

Neuron 1392 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.6681. Min Act: -0.0002

Data Index: 1162354 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.3996. Min Act: -0.0002

Data Index: 560369 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.3609. Min Act: -0.0001

Data Index: 61253 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.3065. Min Act: -0.0002

Data Index: 1054988 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.2350. Min Act: -0.0001

Data Index: 654594 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.2960. Min Act: -0.0001

Data Index: 466736 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.2661. Min Act: -0.0002

Data Index: 254066 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.2091. Min Act: -0.0002

Data Index: 409012 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.2084. Min Act: -0.0001

Data Index: 1114697 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.1997. Min Act: -0.0001

Data Index: 604643 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.1564. Min Act: -0.0001

Data Index: 1226960 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.1489. Min Act: -0.0002

Data Index: 1135979 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.2563. Min Act: -0.0001

Data Index: 353125 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.1728. Min Act: -0.0001

Data Index: 403102 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.0995. Min Act: -0.0001

Data Index: 101288 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.1685. Min Act: -0.0002

Data Index: 284752 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.1557. Min Act: -0.0002

Data Index: 595618 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.1756. Min Act: -0.0001

Data Index: 411760 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.0821. Min Act: -0.0002

Data Index: 1118247 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 1.6681. Min Range: -1.6681

Max Act: 1.2027. Min Act: -0.0002

Data Index: 493555 (C4 (Web Text))

Max Activating Token Index: 809