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

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

Neuron 3156 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.8749. Min Act: -0.0000

Data Index: 696126 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.6209. Min Act: -0.0000

Data Index: 437684 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.5978. Min Act: -0.0000

Data Index: 806681 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.5220. Min Act: -0.0000

Data Index: 175499 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.7058. Min Act: -0.0000

Data Index: 376251 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.6673. Min Act: -0.0000

Data Index: 141301 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.5001. Min Act: -0.0000

Data Index: 282128 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.4550. Min Act: -0.0000

Data Index: 85994 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.2701. Min Act: -0.0000

Data Index: 507741 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.4220. Min Act: -0.0000

Data Index: 692743 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.4766. Min Act: -0.0000

Data Index: 701295 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.6068. Min Act: -0.0000

Data Index: 1026732 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.4657. Min Act: -0.0000

Data Index: 1131417 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.2336. Min Act: -0.0000

Data Index: 523474 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.4006. Min Act: -0.0000

Data Index: 569703 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.3433. Min Act: -0.0000

Data Index: 766385 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.5359. Min Act: -0.0000

Data Index: 772948 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.3110. Min Act: -0.0000

Data Index: 1112802 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.3345. Min Act: -0.0000

Data Index: 901060 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.3049. Min Act: -0.0000

Data Index: 572899 (C4 (Web Text))

Max Activating Token Index: 51