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

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

Neuron 4468 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: 2.8357. Min Range: -2.8357

Max Act: 2.8357. Min Act: -0.0000

Data Index: 1191654 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.6087. Min Act: -0.0000

Data Index: 359563 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.5756. Min Act: -0.0000

Data Index: 891656 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.4123. Min Act: -0.0000

Data Index: 1193574 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.3791. Min Act: -0.0000

Data Index: 749840 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.4568. Min Act: -0.0000

Data Index: 884881 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.4434. Min Act: -0.0000

Data Index: 666237 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.2984. Min Act: -0.0000

Data Index: 499615 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.2757. Min Act: -0.0000

Data Index: 924940 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.3262. Min Act: -0.0000

Data Index: 358747 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.3307. Min Act: -0.0000

Data Index: 345174 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.3209. Min Act: -0.0000

Data Index: 1164246 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.0369. Min Act: -0.0000

Data Index: 760042 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.1525. Min Act: -0.0000

Data Index: 423361 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.3725. Min Act: -0.0000

Data Index: 664728 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.3644. Min Act: -0.0000

Data Index: 116683 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.1240. Min Act: -0.0000

Data Index: 1136154 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.2148. Min Act: -0.0000

Data Index: 845649 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.1904. Min Act: -0.0000

Data Index: 461923 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 2.8357. Min Range: -2.8357

Max Act: 2.2855. Min Act: -0.0000

Data Index: 790101 (C4 (Web Text))

Max Activating Token Index: 334