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

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

Neuron 2595 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.3314. Min Act: -0.0000

Data Index: 697324 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1126773 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.3059. Min Act: -0.0001

Data Index: 486059 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.3076. Min Act: -0.0000

Data Index: 94093 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1123670 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1180301 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2898. Min Act: -0.0000

Data Index: 38008 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2707. Min Act: -0.0000

Data Index: 442908 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2644. Min Act: -0.0000

Data Index: 204935 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2613. Min Act: -0.0001

Data Index: 622190 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2530. Min Act: -0.0000

Data Index: 693207 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2678. Min Act: -0.0000

Data Index: 926730 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2594. Min Act: -0.0000

Data Index: 495042 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2535. Min Act: -0.0000

Data Index: 776427 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2375. Min Act: -0.0000

Data Index: 256887 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1084513 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2374. Min Act: -0.0000

Data Index: 78616 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2219. Min Act: -0.0000

Data Index: 643916 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2367. Min Act: -0.0000

Data Index: 619019 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2291. Min Act: -0.0000

Data Index: 78651 (C4 (Web Text))

Max Activating Token Index: 700