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

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

Neuron 4269 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3893. Min Act: -0.0000

Data Index: 49712 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3990. Min Act: -0.0000

Data Index: 61673 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1348303 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3975. Min Act: -0.0000

Data Index: 400292 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3765. Min Act: -0.0000

Data Index: 142337 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3620. Min Act: -0.0000

Data Index: 334779 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3609. Min Act: -0.0000

Data Index: 103570 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3544. Min Act: -0.0000

Data Index: 669971 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1232962 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3341. Min Act: -0.0000

Data Index: 890786 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3417. Min Act: -0.0000

Data Index: 711287 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3178. Min Act: -0.0000

Data Index: 867284 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3221. Min Act: -0.0000

Data Index: 373968 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2993. Min Act: -0.0000

Data Index: 891702 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3098. Min Act: -0.0000

Data Index: 239968 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3083. Min Act: -0.0000

Data Index: 971047 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3272. Min Act: -0.0000

Data Index: 883155 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2992. Min Act: -0.0000

Data Index: 352566 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1300982 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2837. Min Act: -0.0000

Data Index: 689818 (C4 (Web Text))

Max Activating Token Index: 269