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

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

Neuron 242 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.5529. Min Act: -0.0001

Data Index: 1325324 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3787. Min Act: -0.0001

Data Index: 726825 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4141. Min Act: -0.0001

Data Index: 614378 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2856. Min Act: -0.0001

Data Index: 454293 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1912. Min Act: -0.0001

Data Index: 298449 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2184. Min Act: -0.0001

Data Index: 958841 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2122. Min Act: -0.0001

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1664. Min Act: -0.0000

Data Index: 128782 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0726. Min Act: -0.0001

Data Index: 502758 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2286. Min Act: -0.0001

Data Index: 1072016 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1850. Min Act: -0.0001

Data Index: 1315017 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1426. Min Act: -0.0001

Data Index: 9685 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2595. Min Act: -0.0001

Data Index: 156482 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1299. Min Act: -0.0001

Data Index: 562752 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1340. Min Act: -0.0001

Data Index: 509917 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1926. Min Act: -0.0000

Data Index: 1065991 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1287. Min Act: -0.0000

Data Index: 1128033 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1251. Min Act: -0.0001

Data Index: 751549 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0727. Min Act: -0.0001

Data Index: 439325 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0516. Min Act: -0.0001

Data Index: 555238 (C4 (Web Text))

Max Activating Token Index: 725