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

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

Neuron 2473 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: 0.6155. Min Range: -0.6155

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1135346 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.5684. Min Act: -0.0000

Data Index: 159123 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4993. Min Act: -0.0000

Data Index: 601766 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4689. Min Act: -0.0000

Data Index: 390052 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4467. Min Act: -0.0000

Data Index: 506188 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4661. Min Act: -0.0000

Data Index: 460151 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4222. Min Act: -0.0000

Data Index: 406351 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4327. Min Act: -0.0000

Data Index: 321633 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1008715 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4284. Min Act: -0.0000

Data Index: 383194 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1150732 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4616. Min Act: -0.0000

Data Index: 646797 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4306. Min Act: -0.0000

Data Index: 599003 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.3984. Min Act: -0.0000

Data Index: 310708 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1041844 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4316. Min Act: -0.0000

Data Index: 797133 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4117. Min Act: -0.0000

Data Index: 270697 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1230053 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.3990. Min Act: -0.0000

Data Index: 691286 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.6155. Min Range: -0.6155

Max Act: 0.4220. Min Act: -0.0000

Data Index: 712790 (C4 (Web Text))

Max Activating Token Index: 533