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

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

Neuron 3902 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.4257. Min Act: -0.0000

Data Index: 908845 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.3656. Min Act: -0.0000

Data Index: 751095 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.3300. Min Act: -0.0000

Data Index: 819474 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1346232 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1169983 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2967. Min Act: -0.0000

Data Index: 573807 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2949. Min Act: -0.0000

Data Index: 773754 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1069438 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2933. Min Act: -0.0000

Data Index: 276122 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2998. Min Act: -0.0000

Data Index: 13740 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2854. Min Act: -0.0000

Data Index: 35473 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1160300 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1119743 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2767. Min Act: -0.0000

Data Index: 471631 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2810. Min Act: -0.0000

Data Index: 261596 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1116507 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1189930 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2650. Min Act: -0.0000

Data Index: 824777 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1142436 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.4257. Min Range: -0.4257

Max Act: 0.2452. Min Act: -0.0000

Data Index: 298745 (C4 (Web Text))

Max Activating Token Index: 169