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

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

Neuron 2340 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1313918 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.9407. Min Act: -0.0000

Data Index: 167677 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1159259 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.8002. Min Act: -0.0000

Data Index: 845093 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.8443. Min Act: -0.0000

Data Index: 555463 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.8708. Min Act: -0.0000

Data Index: 344978 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.8381. Min Act: -0.0000

Data Index: 80868 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.8553. Min Act: 0.0005

Data Index: 71641 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.8180. Min Act: -0.0000

Data Index: 460068 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7660. Min Act: -0.0000

Data Index: 837708 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.8190. Min Act: -0.0000

Data Index: 706483 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7964. Min Act: 0.0000

Data Index: 1287194 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7693. Min Act: -0.0000

Data Index: 656558 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.8184. Min Act: -0.0000

Data Index: 690464 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7901. Min Act: -0.0000

Data Index: 208022 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1220294 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.8090. Min Act: -0.0000

Data Index: 855771 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7753. Min Act: -0.0000

Data Index: 255259 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7694. Min Act: -0.0000

Data Index: 168147 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7679. Min Act: -0.0000

Data Index: 727215 (C4 (Web Text))

Max Activating Token Index: 705