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

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

Neuron 3905 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.6290. Min Act: -0.0002

Data Index: 473259 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.4818. Min Act: -0.0002

Data Index: 227428 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.4388. Min Act: -0.0002

Data Index: 43559 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.3092. Min Act: -0.0002

Data Index: 1077973 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.5716. Min Act: -0.0002

Data Index: 215559 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.3971. Min Act: -0.0002

Data Index: 179341 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.5191. Min Act: -0.0002

Data Index: 663141 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2178. Min Act: -0.0002

Data Index: 662091 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2384. Min Act: -0.0002

Data Index: 1254288 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.4823. Min Act: -0.0002

Data Index: 507364 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2768. Min Act: -0.0002

Data Index: 298919 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.0861. Min Act: -0.0002

Data Index: 1122037 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.1321. Min Act: -0.0002

Data Index: 1235324 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2568. Min Act: -0.0002

Data Index: 576799 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.3481. Min Act: -0.0002

Data Index: 713597 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.3910. Min Act: -0.0002

Data Index: 281517 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2458. Min Act: -0.0002

Data Index: 862056 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2215. Min Act: -0.0002

Data Index: 1155537 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.3018. Min Act: -0.0002

Data Index: 619181 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2618. Min Act: -0.0002

Data Index: 123950 (C4 (Web Text))

Max Activating Token Index: 928