Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 507 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1044. Min Range: -1.1044

Max Act: 1.0888. Min Act: -0.0001

Data Index: 925359 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.1044. Min Range: -1.1044

Max Act: 1.1044. Min Act: -0.0001

Data Index: 556897 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 1.1044. Min Range: -1.1044

Max Act: 1.0338. Min Act: -0.0001

Data Index: 817120 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 1.1044. Min Range: -1.1044

Max Act: 1.0413. Min Act: -0.0001

Data Index: 1348921 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9432. Min Act: -0.0001

Data Index: 630151 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1270994 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9405. Min Act: -0.0001

Data Index: 90702 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9320. Min Act: -0.0001

Data Index: 947793 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8535. Min Act: -0.0001

Data Index: 823872 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9179. Min Act: -0.0001

Data Index: 663281 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8903. Min Act: -0.0001

Data Index: 260815 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9665. Min Act: -0.0001

Data Index: 95291 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9066. Min Act: -0.0001

Data Index: 953600 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9564. Min Act: -0.0001

Data Index: 371035 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1168199 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8938. Min Act: -0.0001

Data Index: 258671 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8647. Min Act: -0.0001

Data Index: 15599 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8621. Min Act: -0.0001

Data Index: 253890 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9121. Min Act: -0.0001

Data Index: 388919 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9135. Min Act: -0.0001

Data Index: 383180 (C4 (Web Text))

Max Activating Token Index: 866