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

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

Neuron 2074 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1015687 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0388. Min Act: -0.0001

Data Index: 775593 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0387. Min Act: -0.0001

Data Index: 820721 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1306405 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0384. Min Act: -0.0001

Data Index: 709455 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1237627 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0368. Min Act: -0.0002

Data Index: 428141 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0362. Min Act: -0.0002

Data Index: 921016 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0357. Min Act: -0.0001

Data Index: 559843 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0362. Min Act: -0.0002

Data Index: 430245 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1007844 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0353. Min Act: -0.0002

Data Index: 264377 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0345. Min Act: -0.0002

Data Index: 767543 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0349. Min Act: -0.0002

Data Index: 884953 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1082193 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0354. Min Act: -0.0002

Data Index: 465179 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1335652 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0347. Min Act: -0.0002

Data Index: 43126 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0340. Min Act: -0.0002

Data Index: 547093 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0346. Min Act: -0.0001

Data Index: 539224 (C4 (Web Text))

Max Activating Token Index: 563