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

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

Neuron 3464 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.4423. Min Range: -2.4423

Max Act: 2.4423. Min Act: -0.0002

Data Index: 134243 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 2.4423. Min Range: -2.4423

Max Act: 2.2229. Min Act: -0.0002

Data Index: 85825 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 2.4423. Min Range: -2.4423

Max Act: 2.2917. Min Act: -0.0002

Data Index: 1012977 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 2.4423. Min Range: -2.4423

Max Act: 2.0902. Min Act: -0.0002

Data Index: 1006914 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.9250. Min Act: -0.0003

Data Index: 1107458 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.8746. Min Act: -0.0002

Data Index: 487831 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.8340. Min Act: -0.0002

Data Index: 465667 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.8279. Min Act: -0.0002

Data Index: 1307517 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.7999. Min Act: -0.0002

Data Index: 1118336 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.7642. Min Act: -0.0002

Data Index: 755320 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.7566. Min Act: -0.0002

Data Index: 1032618 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.7445. Min Act: -0.0002

Data Index: 187129 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.7579. Min Act: -0.0002

Data Index: 607773 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.7178. Min Act: -0.0002

Data Index: 370535 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.7148. Min Act: -0.0002

Data Index: 808911 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.7302. Min Act: -0.0002

Data Index: 1022041 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.6477. Min Act: -0.0002

Data Index: 74985 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.6636. Min Act: -0.0002

Data Index: 689718 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.6347. Min Act: -0.0002

Data Index: 138109 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 2.4423. Min Range: -2.4423

Max Act: 1.6852. Min Act: -0.0002

Data Index: 544551 (C4 (Web Text))

Max Activating Token Index: 156