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

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

Neuron 5073 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.4285. Min Act: -0.0000

Data Index: 303171 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3551. Min Act: -0.0000

Data Index: 993051 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1075267 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1270396 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2956. Min Act: -0.0000

Data Index: 189120 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2936. Min Act: -0.0000

Data Index: 677862 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1249101 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2863. Min Act: -0.0000

Data Index: 288143 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2770. Min Act: -0.0000

Data Index: 40402 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2758. Min Act: -0.0000

Data Index: 481248 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2630. Min Act: -0.0000

Data Index: 129438 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1331001 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2538. Min Act: -0.0000

Data Index: 598829 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2533. Min Act: -0.0001

Data Index: 423344 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2472. Min Act: -0.0000

Data Index: 705408 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2469. Min Act: -0.0000

Data Index: 233788 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2448. Min Act: -0.0000

Data Index: 354097 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1059180 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2332. Min Act: -0.0000

Data Index: 273174 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2249. Min Act: -0.0000

Data Index: 1085952 (C4 (Web Text))

Max Activating Token Index: 197