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

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

Neuron 315 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.5372. Min Act: -0.0000

Data Index: 367696 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.1448. Min Act: -0.0000

Data Index: 765200 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.1087. Min Act: -0.0000

Data Index: 444340 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.0338. Min Act: -0.0000

Data Index: 853729 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.9341. Min Act: -0.0000

Data Index: 11359 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.1072. Min Act: -0.0000

Data Index: 40597 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.8929. Min Act: -0.0000

Data Index: 348323 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.7644. Min Act: -0.0000

Data Index: 345097 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.7806. Min Act: -0.0000

Data Index: 11983 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.7309. Min Act: -0.0000

Data Index: 554169 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1275510 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.8641. Min Act: -0.0000

Data Index: 1136232 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1040179 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.8451. Min Act: -0.0000

Data Index: 502106 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.7386. Min Act: -0.0000

Data Index: 962075 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.7591. Min Act: -0.0000

Data Index: 604686 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.6268. Min Act: -0.0000

Data Index: 819524 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.7797. Min Act: -0.0000

Data Index: 86470 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.8248. Min Act: 0.0000

Data Index: 1457524 (Python Code)

Max Activating Token Index: 352

Text #19

Max Range: 2.5372. Min Range: -2.5372

Max Act: 1.7113. Min Act: -0.0000

Data Index: 1130407 (C4 (Web Text))

Max Activating Token Index: 46