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

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

Neuron 5449 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: 3.0139. Min Range: -3.0139

Max Act: 3.0139. Min Act: -0.0002

Data Index: 385838 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.6500. Min Act: -0.0002

Data Index: 787373 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.5746. Min Act: -0.0002

Data Index: 350978 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.5573. Min Act: -0.0003

Data Index: 718566 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.5472. Min Act: -0.0002

Data Index: 894492 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.5216. Min Act: -0.0002

Data Index: 1033359 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.5155. Min Act: -0.0002

Data Index: 339167 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.4393. Min Act: -0.0002

Data Index: 1129531 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.4249. Min Act: -0.0002

Data Index: 860784 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.3644. Min Act: -0.0002

Data Index: 1056146 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.3453. Min Act: -0.0002

Data Index: 1176406 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.2686. Min Act: -0.0002

Data Index: 1066452 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.2227. Min Act: -0.0002

Data Index: 95990 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.2518. Min Act: -0.0002

Data Index: 575129 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.2468. Min Act: -0.0002

Data Index: 769845 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.1799. Min Act: -0.0002

Data Index: 7505 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.2351. Min Act: -0.0002

Data Index: 624360 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.1489. Min Act: -0.0002

Data Index: 973471 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.1490. Min Act: -0.0002

Data Index: 112992 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 3.0139. Min Range: -3.0139

Max Act: 2.1185. Min Act: -0.0002

Data Index: 747444 (C4 (Web Text))

Max Activating Token Index: 1001