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

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

Neuron 2231 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: 0.6623. Min Range: -0.6623

Max Act: 0.6623. Min Act: -0.0000

Data Index: 459486 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5972. Min Act: -0.0000

Data Index: 126920 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5104. Min Act: -0.0000

Data Index: 409891 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.5357. Min Act: -0.0000

Data Index: 24228 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4796. Min Act: -0.0000

Data Index: 727409 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4651. Min Act: -0.0000

Data Index: 914078 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1115808 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1311290 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4605. Min Act: -0.0000

Data Index: 100788 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4432. Min Act: -0.0000

Data Index: 351380 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4747. Min Act: -0.0000

Data Index: 149615 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4904. Min Act: -0.0000

Data Index: 422300 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4686. Min Act: -0.0000

Data Index: 969132 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1153032 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4642. Min Act: -0.0000

Data Index: 865688 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1251635 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4416. Min Act: -0.0000

Data Index: 528176 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4387. Min Act: -0.0000

Data Index: 906231 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4585. Min Act: -0.0000

Data Index: 387969 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.6623. Min Range: -0.6623

Max Act: 0.4151. Min Act: -0.0000

Data Index: 447283 (C4 (Web Text))

Max Activating Token Index: 52