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

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

Neuron 4233 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: 0.7929. Min Range: -0.7929

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1030896 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5297. Min Act: -0.0000

Data Index: 531195 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5070. Min Act: -0.0000

Data Index: 197054 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5130. Min Act: -0.0000

Data Index: 711595 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5144. Min Act: -0.0000

Data Index: 947273 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4898. Min Act: -0.0000

Data Index: 497199 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4516. Min Act: -0.0000

Data Index: 787268 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4623. Min Act: -0.0000

Data Index: 942339 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1217578 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4755. Min Act: -0.0000

Data Index: 419498 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4755. Min Act: -0.0000

Data Index: 533480 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1331563 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4640. Min Act: -0.0000

Data Index: 142980 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4226. Min Act: -0.0000

Data Index: 436721 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4159. Min Act: -0.0000

Data Index: 700431 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4441. Min Act: -0.0000

Data Index: 135516 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4418. Min Act: -0.0000

Data Index: 242688 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.3686. Min Act: -0.0000

Data Index: 42954 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1260003 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.4170. Min Act: -0.0000

Data Index: 497923 (C4 (Web Text))

Max Activating Token Index: 685