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

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

Neuron 3389 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.1826. Min Act: -0.0001

Data Index: 848256 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.1263. Min Act: -0.0001

Data Index: 505038 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0360. Min Act: -0.0001

Data Index: 649314 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9821. Min Act: -0.0001

Data Index: 667528 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0649. Min Act: -0.0001

Data Index: 155930 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0135. Min Act: -0.0001

Data Index: 958410 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9614. Min Act: -0.0001

Data Index: 1290252 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9868. Min Act: -0.0001

Data Index: 1239498 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9222. Min Act: -0.0001

Data Index: 723248 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0131. Min Act: -0.0001

Data Index: 443462 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9661. Min Act: -0.0001

Data Index: 971202 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9791. Min Act: -0.0001

Data Index: 441050 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8885. Min Act: -0.0001

Data Index: 1241580 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9118. Min Act: -0.0001

Data Index: 337448 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1100546 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9123. Min Act: -0.0001

Data Index: 1225008 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8497. Min Act: -0.0001

Data Index: 328691 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8700. Min Act: -0.0001

Data Index: 1211208 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8393. Min Act: -0.0001

Data Index: 996634 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.7827. Min Act: -0.0001

Data Index: 769275 (C4 (Web Text))

Max Activating Token Index: 923