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

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

Neuron 4219 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: 3.9647. Min Range: -3.9647

Max Act: 3.9647. Min Act: -0.0000

Data Index: 148862 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.6616. Min Act: -0.0000

Data Index: 620390 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.4071. Min Act: -0.0000

Data Index: 1155187 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.0451. Min Act: -0.0000

Data Index: 719696 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.3340. Min Act: -0.0000

Data Index: 1233297 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.0521. Min Act: -0.0000

Data Index: 466686 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.0346. Min Act: -0.0000

Data Index: 3190 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.1315. Min Act: -0.0000

Data Index: 1241797 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.9647. Min Range: -3.9647

Max Act: 2.9890. Min Act: -0.0000

Data Index: 671608 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.0596. Min Act: -0.0000

Data Index: 1025437 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 3.9647. Min Range: -3.9647

Max Act: 2.8837. Min Act: -0.0000

Data Index: 1262823 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 3.9647. Min Range: -3.9647

Max Act: 2.8758. Min Act: -0.0000

Data Index: 260995 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.0134. Min Act: -0.0000

Data Index: 975575 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 3.9647. Min Range: -3.9647

Max Act: 2.9529. Min Act: -0.0000

Data Index: 1084912 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.0140. Min Act: -0.0000

Data Index: 969302 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.0082. Min Act: -0.0000

Data Index: 81203 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 3.9647. Min Range: -3.9647

Max Act: 2.7377. Min Act: -0.0000

Data Index: 1287528 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 3.9647. Min Range: -3.9647

Max Act: 2.7062. Min Act: -0.0000

Data Index: 1129136 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 3.9647. Min Range: -3.9647

Max Act: 2.7828. Min Act: -0.0000

Data Index: 686037 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 3.9647. Min Range: -3.9647

Max Act: 2.7642. Min Act: -0.0000

Data Index: 321605 (C4 (Web Text))

Max Activating Token Index: 858