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

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

Neuron 1068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1660. Min Act: -0.0002

Data Index: 834607 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1454. Min Act: -0.0001

Data Index: 604568 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1216. Min Act: -0.0001

Data Index: 405149 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1027. Min Act: -0.0001

Data Index: 1029870 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1029. Min Act: -0.0001

Data Index: 542362 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0602. Min Act: -0.0002

Data Index: 547266 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1249. Min Act: -0.0001

Data Index: 1244864 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1293. Min Act: -0.0001

Data Index: 1286383 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1177. Min Act: -0.0002

Data Index: 215438 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0744. Min Act: -0.0002

Data Index: 542867 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1015. Min Act: -0.0002

Data Index: 634919 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0373. Min Act: -0.0001

Data Index: 103695 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0051. Min Act: -0.0001

Data Index: 703436 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9744. Min Act: -0.0001

Data Index: 126933 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0398. Min Act: -0.0001

Data Index: 239874 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0353. Min Act: -0.0001

Data Index: 194977 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0349. Min Act: -0.0001

Data Index: 379900 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0249. Min Act: -0.0001

Data Index: 435858 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0532. Min Act: -0.0002

Data Index: 227936 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9967. Min Act: -0.0002

Data Index: 465388 (C4 (Web Text))

Max Activating Token Index: 849