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

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

Neuron 642 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: 1.7580. Min Range: -1.7580

Max Act: 1.7580. Min Act: -0.0002

Data Index: 1144891 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.6431. Min Act: -0.0002

Data Index: 1023745 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.6332. Min Act: -0.0002

Data Index: 472962 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.6024. Min Act: -0.0002

Data Index: 114098 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.5330. Min Act: -0.0002

Data Index: 577678 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4623. Min Act: -0.0002

Data Index: 76302 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4168. Min Act: -0.0002

Data Index: 1354944 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3586. Min Act: -0.0002

Data Index: 464734 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3490. Min Act: -0.0002

Data Index: 601456 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3615. Min Act: -0.0002

Data Index: 431766 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3902. Min Act: -0.0002

Data Index: 266007 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3888. Min Act: -0.0002

Data Index: 466235 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3770. Min Act: -0.0002

Data Index: 694356 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3426. Min Act: -0.0002

Data Index: 1308014 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3484. Min Act: -0.0002

Data Index: 524485 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3649. Min Act: -0.0002

Data Index: 586914 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3939. Min Act: -0.0002

Data Index: 255151 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3047. Min Act: -0.0002

Data Index: 49206 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3021. Min Act: -0.0002

Data Index: 1184552 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3362. Min Act: -0.0002

Data Index: 81515 (C4 (Web Text))

Max Activating Token Index: 48