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

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

Neuron 1393 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4037. Min Range: -4.4037

Max Act: 4.0633. Min Act: -0.0001

Data Index: 1576976 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 4.4037. Min Range: -4.4037

Max Act: 4.4037. Min Act: -0.0001

Data Index: 1370006 (Python Code)

Max Activating Token Index: 392

Text #2

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.7925. Min Act: -0.0001

Data Index: 1442951 (Python Code)

Max Activating Token Index: 396

Text #3

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.7555. Min Act: -0.0001

Data Index: 1441485 (Python Code)

Max Activating Token Index: 793

Text #4

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.6750. Min Act: -0.0001

Data Index: 650175 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.5702. Min Act: -0.0001

Data Index: 1499571 (Python Code)

Max Activating Token Index: 485

Text #6

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.3609. Min Act: -0.0001

Data Index: 1528267 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.2684. Min Act: -0.0001

Data Index: 1569919 (Python Code)

Max Activating Token Index: 518

Text #8

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.3986. Min Act: -0.0001

Data Index: 1370682 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.2647. Min Act: -0.0001

Data Index: 223026 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.2570. Min Act: -0.0001

Data Index: 1410018 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.2169. Min Act: -0.0001

Data Index: 1624809 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.6307. Min Act: -0.0001

Data Index: 606262 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.2114. Min Act: -0.0001

Data Index: 1500178 (Python Code)

Max Activating Token Index: 928

Text #14

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.3133. Min Act: -0.0001

Data Index: 1596186 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.3054. Min Act: -0.0001

Data Index: 1035600 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.6254. Min Act: -0.0001

Data Index: 1035374 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.1388. Min Act: -0.0001

Data Index: 1583475 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.4187. Min Act: -0.0001

Data Index: 1647833 (Python Code)

Max Activating Token Index: 469

Text #19

Max Range: 4.4037. Min Range: -4.4037

Max Act: 3.2184. Min Act: -0.0001

Data Index: 1412221 (Python Code)

Max Activating Token Index: 73