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

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

Neuron 4326 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.4784. Min Act: -0.0000

Data Index: 315195 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.4469. Min Act: -0.0000

Data Index: 993109 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.3578. Min Act: -0.0000

Data Index: 607251 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.3088. Min Act: -0.0000

Data Index: 16 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.2426. Min Act: -0.0000

Data Index: 839603 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.2325. Min Act: -0.0000

Data Index: 1621374 (Python Code)

Max Activating Token Index: 511

Text #6

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.2256. Min Act: -0.0000

Data Index: 258129 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.1784. Min Act: -0.0000

Data Index: 459391 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.0029. Min Act: -0.0000

Data Index: 1091072 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.0661. Min Act: -0.0000

Data Index: 230042 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.0748. Min Act: -0.0000

Data Index: 1034784 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.1435. Min Act: -0.0000

Data Index: 359502 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.0256. Min Act: -0.0000

Data Index: 1142767 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.4784. Min Range: -2.4784

Max Act: 1.9214. Min Act: -0.0000

Data Index: 29281 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 2.4784. Min Range: -2.4784

Max Act: 2.0193. Min Act: -0.0000

Data Index: 581400 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 2.4784. Min Range: -2.4784

Max Act: 1.8862. Min Act: -0.0000

Data Index: 778317 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 2.4784. Min Range: -2.4784

Max Act: 1.9998. Min Act: -0.0000

Data Index: 392980 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 2.4784. Min Range: -2.4784

Max Act: 1.9791. Min Act: -0.0000

Data Index: 782711 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 2.4784. Min Range: -2.4784

Max Act: 1.9903. Min Act: -0.0000

Data Index: 524630 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 2.4784. Min Range: -2.4784

Max Act: 1.9702. Min Act: -0.0000

Data Index: 496784 (C4 (Web Text))

Max Activating Token Index: 324