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

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

Neuron 5435 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.3437. Min Act: -0.0000

Data Index: 426326 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.2615. Min Act: -0.0000

Data Index: 81565 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.2344. Min Act: -0.0000

Data Index: 1173701 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.2070. Min Act: -0.0000

Data Index: 1086834 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.0575. Min Act: -0.0000

Data Index: 996651 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.1821. Min Act: -0.0000

Data Index: 906126 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.1430. Min Act: -0.0000

Data Index: 450875 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.0199. Min Act: -0.0000

Data Index: 776865 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.0799. Min Act: -0.0000

Data Index: 1041570 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 2.3437. Min Range: -2.3437

Max Act: 1.9735. Min Act: -0.0000

Data Index: 604386 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.0565. Min Act: -0.0000

Data Index: 313118 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.0245. Min Act: -0.0000

Data Index: 3221 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 2.3437. Min Range: -2.3437

Max Act: 1.9137. Min Act: -0.0000

Data Index: 1329663 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 2.3437. Min Range: -2.3437

Max Act: 1.9915. Min Act: -0.0000

Data Index: 967901 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.0095. Min Act: -0.0000

Data Index: 786476 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.1229. Min Act: -0.0000

Data Index: 1026803 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 2.3437. Min Range: -2.3437

Max Act: 2.0868. Min Act: -0.0000

Data Index: 1300354 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 2.3437. Min Range: -2.3437

Max Act: 1.8751. Min Act: -0.0000

Data Index: 808478 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 2.3437. Min Range: -2.3437

Max Act: 1.9487. Min Act: -0.0000

Data Index: 123662 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 2.3437. Min Range: -2.3437

Max Act: 1.8368. Min Act: -0.0000

Data Index: 1031941 (C4 (Web Text))

Max Activating Token Index: 800