Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2378 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0463. Min Act: -0.0003

Data Index: 373444 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0414. Min Act: -0.0003

Data Index: 363870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0332. Min Act: -0.0003

Data Index: 606145 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0322. Min Act: -0.0003

Data Index: 233916 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0319. Min Act: -0.0003

Data Index: 669203 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0316. Min Act: -0.0004

Data Index: 787918 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1145420 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0304. Min Act: -0.0004

Data Index: 1045062 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0293. Min Act: -0.0003

Data Index: 449925 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1121735 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0296. Min Act: -0.0004

Data Index: 1102124 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0275. Min Act: -0.0003

Data Index: 211587 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1450777 (Python Code)

Max Activating Token Index: 761

Text #13

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0274. Min Act: -0.0003

Data Index: 322630 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0263. Min Act: -0.0003

Data Index: 796410 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0267. Min Act: -0.0003

Data Index: 772358 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1418889 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1147800 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0261. Min Act: -0.0004

Data Index: 1209745 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0256. Min Act: -0.0003

Data Index: 291482 (C4 (Web Text))

Max Activating Token Index: 1023