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

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

Neuron 3856 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1114185 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4283. Min Act: -0.0000

Data Index: 810497 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4251. Min Act: -0.0000

Data Index: 988249 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4748. Min Act: -0.0000

Data Index: 781233 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4173. Min Act: -0.0000

Data Index: 809264 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4018. Min Act: -0.0000

Data Index: 291652 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3913. Min Act: -0.0000

Data Index: 594402 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1276743 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3056. Min Act: -0.0000

Data Index: 206743 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3847. Min Act: 0.0000

Data Index: 517769 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1216397 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4054. Min Act: -0.0000

Data Index: 84761 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1069945 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3736. Min Act: -0.0000

Data Index: 814437 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3380. Min Act: 0.0000

Data Index: 714517 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3587. Min Act: -0.0000

Data Index: 739471 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3741. Min Act: -0.0000

Data Index: 628917 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3571. Min Act: -0.0000

Data Index: 262745 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3622. Min Act: -0.0000

Data Index: 774009 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3926. Min Act: -0.0000

Data Index: 560998 (C4 (Web Text))

Max Activating Token Index: 681