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

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

Neuron 1310 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: 3.0665. Min Range: -3.0665

Max Act: 3.0665. Min Act: -0.0000

Data Index: 123383 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 3.0665. Min Range: -3.0665

Max Act: 3.0390. Min Act: -0.0000

Data Index: 890754 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 3.0665. Min Range: -3.0665

Max Act: 3.0475. Min Act: -0.0000

Data Index: 212720 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 3.0665. Min Range: -3.0665

Max Act: 3.0023. Min Act: -0.0001

Data Index: 1082406 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.9538. Min Act: -0.0000

Data Index: 599677 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8718. Min Act: -0.0000

Data Index: 709910 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8707. Min Act: -0.0000

Data Index: 314811 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8763. Min Act: -0.0000

Data Index: 347604 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8037. Min Act: -0.0000

Data Index: 1104655 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.7942. Min Act: -0.0000

Data Index: 853072 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.6578. Min Act: -0.0000

Data Index: 1329372 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.6659. Min Act: -0.0000

Data Index: 860235 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.7904. Min Act: -0.0000

Data Index: 569773 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.8210. Min Act: -0.0000

Data Index: 1115761 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.7739. Min Act: -0.0000

Data Index: 1224171 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.7356. Min Act: -0.0000

Data Index: 687963 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.7760. Min Act: -0.0000

Data Index: 1187481 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.6192. Min Act: -0.0000

Data Index: 1314714 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.6165. Min Act: -0.0000

Data Index: 1159946 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.7115. Min Act: -0.0000

Data Index: 588869 (C4 (Web Text))

Max Activating Token Index: 864