Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2634 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.7438. Min Act: -0.0001

Data Index: 128533 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.6407. Min Act: -0.0001

Data Index: 280983 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.6430. Min Act: -0.0001

Data Index: 227145 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.5542. Min Act: -0.0001

Data Index: 1318116 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.5942. Min Act: -0.0001

Data Index: 816887 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.5675. Min Act: -0.0001

Data Index: 600864 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.5598. Min Act: -0.0001

Data Index: 388975 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4577. Min Act: -0.0001

Data Index: 1348868 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4840. Min Act: -0.0001

Data Index: 738031 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4355. Min Act: -0.0001

Data Index: 1019001 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.5196. Min Act: -0.0001

Data Index: 306513 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4760. Min Act: -0.0001

Data Index: 785260 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4672. Min Act: -0.0001

Data Index: 17327 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4334. Min Act: -0.0001

Data Index: 1348881 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4312. Min Act: -0.0001

Data Index: 641558 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.3763. Min Act: -0.0001

Data Index: 835103 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4188. Min Act: -0.0001

Data Index: 275941 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4541. Min Act: -0.0001

Data Index: 262150 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.4573. Min Act: -0.0001

Data Index: 764019 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 1.7438. Min Range: -1.7438

Max Act: 1.3687. Min Act: -0.0001

Data Index: 168874 (C4 (Web Text))

Max Activating Token Index: 324