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

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

Neuron 907 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0000

Data Index: 28802 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0644. Min Act: -0.0000

Data Index: 151466 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0537. Min Act: -0.0000

Data Index: 40954 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0483. Min Act: -0.0000

Data Index: 310790 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1187723 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1228050 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0413. Min Act: -0.0000

Data Index: 136985 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0440. Min Act: -0.0000

Data Index: 115296 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1353153 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0426. Min Act: -0.0000

Data Index: 408191 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0418. Min Act: -0.0000

Data Index: 369930 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0413. Min Act: -0.0000

Data Index: 1480456 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0388. Min Act: -0.0000

Data Index: 119191 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0383. Min Act: -0.0000

Data Index: 920776 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0396. Min Act: -0.0000

Data Index: 117818 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0374. Min Act: -0.0000

Data Index: 781832 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0381. Min Act: -0.0000

Data Index: 634745 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1181808 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0346. Min Act: -0.0000

Data Index: 305785 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1444623 (Python Code)

Max Activating Token Index: 624