Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 715 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0100. Min Range: -2.0100

Max Act: 2.0100. Min Act: -0.0000

Data Index: 1302564 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.7892. Min Act: -0.0000

Data Index: 1228860 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.5590. Min Act: -0.0000

Data Index: 685326 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.6663. Min Act: 0.0000

Data Index: 694765 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.4940. Min Act: -0.0000

Data Index: 913941 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.4553. Min Act: 0.0000

Data Index: 748038 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.4358. Min Act: -0.0000

Data Index: 815767 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.4315. Min Act: -0.0000

Data Index: 715731 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.3308. Min Act: -0.0000

Data Index: 349006 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.3773. Min Act: -0.0000

Data Index: 28628 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1059382 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1002195 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.3159. Min Act: -0.0000

Data Index: 348191 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.2858. Min Act: -0.0000

Data Index: 783073 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.2683. Min Act: -0.0000

Data Index: 236638 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.2710. Min Act: -0.0000

Data Index: 224385 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.2550. Min Act: -0.0000

Data Index: 546614 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.3069. Min Act: -0.0000

Data Index: 470505 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.3157. Min Act: 0.0000

Data Index: 368975 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 2.0100. Min Range: -2.0100

Max Act: 1.2219. Min Act: -0.0000

Data Index: 616541 (C4 (Web Text))

Max Activating Token Index: 75