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

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

Neuron 4326 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1235044 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.5532. Min Act: -0.0000

Data Index: 344783 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.5050. Min Act: -0.0000

Data Index: 554044 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.5010. Min Act: -0.0000

Data Index: 597917 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.4897. Min Act: -0.0000

Data Index: 717910 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1149022 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.4204. Min Act: -0.0000

Data Index: 28182 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1213571 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1162692 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.4067. Min Act: -0.0000

Data Index: 57516 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.4052. Min Act: -0.0000

Data Index: 62054 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1321382 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1069005 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.3823. Min Act: -0.0000

Data Index: 889145 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.3794. Min Act: -0.0000

Data Index: 36026 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.3788. Min Act: -0.0000

Data Index: 43001 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1110003 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1257790 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.3757. Min Act: -0.0000

Data Index: 84575 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1208384 (C4 (Web Text))

Max Activating Token Index: 133