Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 874 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.6176. Min Act: -0.0001

Data Index: 1109606 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5807. Min Act: -0.0001

Data Index: 908917 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.3559. Min Act: -0.0001

Data Index: 369982 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.4635. Min Act: -0.0001

Data Index: 880812 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.5707. Min Act: -0.0001

Data Index: 486947 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.3436. Min Act: -0.0001

Data Index: 438432 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.3666. Min Act: -0.0001

Data Index: 15791 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.2839. Min Act: -0.0001

Data Index: 1255495 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.3248. Min Act: -0.0001

Data Index: 1187386 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.2517. Min Act: -0.0001

Data Index: 150831 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.2708. Min Act: -0.0001

Data Index: 230770 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.3251. Min Act: -0.0001

Data Index: 1182297 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.2199. Min Act: -0.0001

Data Index: 1136795 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.2575. Min Act: -0.0001

Data Index: 958459 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.2553. Min Act: -0.0001

Data Index: 409783 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.2809. Min Act: -0.0001

Data Index: 781486 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.2585. Min Act: -0.0001

Data Index: 133329 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.0286. Min Act: -0.0001

Data Index: 403812 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.2340. Min Act: -0.0001

Data Index: 548875 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.6176. Min Range: -1.6176

Max Act: 1.1562. Min Act: -0.0001

Data Index: 45414 (C4 (Web Text))

Max Activating Token Index: 773