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

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

Neuron 3932 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1524161 (Python Code)

Max Activating Token Index: 1004

Text #1

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0433. Min Act: -0.0001

Data Index: 824514 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0413. Min Act: -0.0001

Data Index: 995485 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1490628 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0385. Min Act: -0.0001

Data Index: 396941 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1315130 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0379. Min Act: -0.0001

Data Index: 569077 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0351. Min Act: -0.0001

Data Index: 938175 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0348. Min Act: -0.0001

Data Index: 683172 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0360. Min Act: -0.0001

Data Index: 201390 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0399. Min Act: -0.0001

Data Index: 190974 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1512673 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0374. Min Act: -0.0001

Data Index: 995947 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1505922 (Python Code)

Max Activating Token Index: 951

Text #14

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0361. Min Act: -0.0001

Data Index: 718309 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1374194 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0339. Min Act: -0.0001

Data Index: 982810 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0344. Min Act: -0.0001

Data Index: 847920 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0336. Min Act: -0.0001

Data Index: 264110 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0359. Min Act: -0.0001

Data Index: 259991 (C4 (Web Text))

Max Activating Token Index: 1019