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

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

Neuron 3975 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.6536. Min Act: -0.0000

Data Index: 118436 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5707. Min Act: -0.0000

Data Index: 214218 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.6226. Min Act: -0.0000

Data Index: 268424 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5353. Min Act: -0.0000

Data Index: 658042 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1129161 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4585. Min Act: -0.0000

Data Index: 47976 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4723. Min Act: -0.0000

Data Index: 204336 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4511. Min Act: -0.0000

Data Index: 228652 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4735. Min Act: -0.0000

Data Index: 916095 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4568. Min Act: -0.0000

Data Index: 702345 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1133977 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4357. Min Act: -0.0000

Data Index: 676212 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4354. Min Act: -0.0000

Data Index: 456793 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1152571 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4575. Min Act: -0.0000

Data Index: 710998 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4194. Min Act: -0.0000

Data Index: 892571 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1256920 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1180078 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4208. Min Act: -0.0000

Data Index: 465987 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4364. Min Act: -0.0000

Data Index: 186097 (C4 (Web Text))

Max Activating Token Index: 404