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

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

Neuron 3369 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.5105. Min Act: -0.0001

Data Index: 774473 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.5456. Min Act: -0.0001

Data Index: 1053619 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.4886. Min Act: -0.0001

Data Index: 1091983 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.2923. Min Act: -0.0001

Data Index: 353326 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.4867. Min Act: -0.0001

Data Index: 1338600 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.4056. Min Act: -0.0001

Data Index: 756483 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.3363. Min Act: -0.0001

Data Index: 59006 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.3233. Min Act: -0.0001

Data Index: 143772 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.4073. Min Act: -0.0001

Data Index: 382506 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.2372. Min Act: -0.0001

Data Index: 21099 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.2898. Min Act: -0.0001

Data Index: 931530 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.4503. Min Act: -0.0001

Data Index: 1069518 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.2207. Min Act: -0.0001

Data Index: 914115 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.2236. Min Act: -0.0001

Data Index: 566545 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.3509. Min Act: -0.0001

Data Index: 51855 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.2008. Min Act: -0.0001

Data Index: 1168127 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.1868. Min Act: -0.0001

Data Index: 398003 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.1466. Min Act: -0.0001

Data Index: 67071 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.1635. Min Act: -0.0001

Data Index: 1232847 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.8355. Min Act: -0.0001

Data Index: 622113 (C4 (Web Text))

Max Activating Token Index: 814