Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3681. Min Act: -0.0003

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3521. Min Act: -0.0003

Data Index: 1647089 (Python Code)

Max Activating Token Index: 675

Text #2

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2703. Min Act: -0.0003

Data Index: 744936 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2564. Min Act: -0.0003

Data Index: 454759 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2627. Min Act: -0.0003

Data Index: 1092392 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2476. Min Act: -0.0003

Data Index: 858184 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2429. Min Act: -0.0003

Data Index: 145242 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2393. Min Act: -0.0003

Data Index: 1090252 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2374. Min Act: -0.0003

Data Index: 1114194 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2345. Min Act: -0.0003

Data Index: 975124 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2344. Min Act: -0.0003

Data Index: 239508 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2331. Min Act: -0.0003

Data Index: 515342 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2295. Min Act: -0.0003

Data Index: 194581 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2366. Min Act: -0.0003

Data Index: 1165128 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2121. Min Act: -0.0003

Data Index: 203864 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2258. Min Act: -0.0004

Data Index: 380521 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2212. Min Act: -0.0003

Data Index: 434675 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2203. Min Act: -0.0003

Data Index: 939694 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2458. Min Act: -0.0004

Data Index: 487357 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2195. Min Act: -0.0003

Data Index: 298660 (C4 (Web Text))

Max Activating Token Index: 340