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

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

Neuron 2184 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: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1159205 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0395. Min Act: -0.0003

Data Index: 622747 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0407. Min Act: -0.0003

Data Index: 363783 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1364894 (Python Code)

Max Activating Token Index: 153

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0340. Min Act: -0.0003

Data Index: 279658 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0384. Min Act: -0.0003

Data Index: 537172 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0348. Min Act: -0.0003

Data Index: 565459 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1631040 (Python Code)

Max Activating Token Index: 989

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0342. Min Act: -0.0003

Data Index: 916227 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0346. Min Act: -0.0003

Data Index: 698801 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0357. Min Act: -0.0003

Data Index: 17839 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0317. Min Act: -0.0003

Data Index: 66517 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1392621 (Python Code)

Max Activating Token Index: 524

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1603076 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0346. Min Act: -0.0003

Data Index: 987492 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0343. Min Act: -0.0003

Data Index: 156832 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0340. Min Act: -0.0003

Data Index: 386203 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0328. Min Act: -0.0003

Data Index: 424903 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0336. Min Act: -0.0003

Data Index: 867381 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0333. Min Act: -0.0003

Data Index: 246907 (C4 (Web Text))

Max Activating Token Index: 397