Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 882 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0005

Data Index: 945354 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0323. Min Act: -0.0005

Data Index: 677403 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0311. Min Act: -0.0005

Data Index: 1323708 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0335. Min Act: -0.0005

Data Index: 486354 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0311. Min Act: -0.0005

Data Index: 889861 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0311. Min Act: -0.0005

Data Index: 337811 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0301. Min Act: -0.0005

Data Index: 799741 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0309. Min Act: -0.0005

Data Index: 982844 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0301. Min Act: -0.0005

Data Index: 912113 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0298. Min Act: -0.0005

Data Index: 966841 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0289. Min Act: -0.0005

Data Index: 645729 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0293. Min Act: -0.0005

Data Index: 862987 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0272. Min Act: -0.0005

Data Index: 43927 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1419727 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0277. Min Act: -0.0005

Data Index: 584305 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0282. Min Act: -0.0005

Data Index: 1105146 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0286. Min Act: -0.0005

Data Index: 402995 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1086998 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0269. Min Act: -0.0005

Data Index: 675541 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0264. Min Act: -0.0005

Data Index: 1021096 (C4 (Web Text))

Max Activating Token Index: 561