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

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

Neuron 3994 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.7113. Min Act: -0.0000

Data Index: 1166346 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.7958. Min Act: -0.0000

Data Index: 275564 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.5766. Min Act: -0.0000

Data Index: 813147 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.5399. Min Act: -0.0000

Data Index: 427619 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.3552. Min Act: -0.0000

Data Index: 954557 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.3037. Min Act: -0.0000

Data Index: 575223 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.0781. Min Act: -0.0000

Data Index: 932093 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1672. Min Act: -0.0000

Data Index: 432293 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.2325. Min Act: -0.0000

Data Index: 770821 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1621. Min Act: -0.0000

Data Index: 617459 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1697. Min Act: -0.0000

Data Index: 1144593 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1615. Min Act: -0.0000

Data Index: 1153857 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1988. Min Act: -0.0000

Data Index: 437796 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1337700 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.2529. Min Act: -0.0000

Data Index: 954074 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1733. Min Act: -0.0000

Data Index: 815722 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.2440. Min Act: -0.0000

Data Index: 495642 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.0952. Min Act: -0.0000

Data Index: 584417 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1503. Min Act: -0.0000

Data Index: 375163 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1540. Min Act: -0.0000

Data Index: 802059 (C4 (Web Text))

Max Activating Token Index: 670