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

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

Neuron 983 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.7288. Min Act: -0.0000

Data Index: 841271 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.7350. Min Act: -0.0000

Data Index: 245945 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.7113. Min Act: -0.0000

Data Index: 456950 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6058. Min Act: -0.0000

Data Index: 206527 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6942. Min Act: -0.0000

Data Index: 194272 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6389. Min Act: -0.0000

Data Index: 702790 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6669. Min Act: -0.0000

Data Index: 376592 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6206. Min Act: -0.0000

Data Index: 166885 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6125. Min Act: -0.0000

Data Index: 22207 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1011676 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6197. Min Act: -0.0000

Data Index: 525113 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6134. Min Act: -0.0000

Data Index: 467332 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1250393 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5326. Min Act: -0.0000

Data Index: 286531 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5592. Min Act: -0.0000

Data Index: 973660 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5522. Min Act: -0.0000

Data Index: 556837 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5325. Min Act: -0.0000

Data Index: 437876 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5496. Min Act: -0.0000

Data Index: 283599 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5477. Min Act: -0.0000

Data Index: 799153 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.7350. Min Range: -0.7350

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1359301 (C4 (Web Text))

Max Activating Token Index: 354