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

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

Neuron 485 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0465. Min Act: -0.0003

Data Index: 883686 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0438. Min Act: -0.0003

Data Index: 714265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0373. Min Act: -0.0003

Data Index: 302439 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0336. Min Act: -0.0003

Data Index: 205682 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0335. Min Act: -0.0003

Data Index: 989258 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0324. Min Act: -0.0003

Data Index: 575922 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0342. Min Act: -0.0003

Data Index: 917567 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0331. Min Act: -0.0003

Data Index: 735449 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0315. Min Act: -0.0003

Data Index: 230499 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0345. Min Act: -0.0003

Data Index: 956474 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0343. Min Act: -0.0003

Data Index: 827233 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0327. Min Act: -0.0003

Data Index: 838534 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1345485 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0271. Min Act: -0.0003

Data Index: 923391 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1028945 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1080672 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0298. Min Act: -0.0003

Data Index: 556100 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1331064 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1348418 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0320. Min Act: -0.0004

Data Index: 710793 (C4 (Web Text))

Max Activating Token Index: 335