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

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

Neuron 2857 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0283. Min Act: -0.0001

Data Index: 679468 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0298. Min Act: -0.0001

Data Index: 489804 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0001

Data Index: 569643 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1162280 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1122712 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1121810 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0304. Min Act: -0.0001

Data Index: 192235 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0292. Min Act: -0.0001

Data Index: 390 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0283. Min Act: -0.0001

Data Index: 717286 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0295. Min Act: -0.0001

Data Index: 299264 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0277. Min Act: -0.0001

Data Index: 349255 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0276. Min Act: -0.0001

Data Index: 657469 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1333296 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0001

Data Index: 809696 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1048839 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0252. Min Act: -0.0001

Data Index: 587679 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0001

Data Index: 539727 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0278. Min Act: -0.0001

Data Index: 346161 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0269. Min Act: -0.0001

Data Index: 503072 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1290180 (C4 (Web Text))

Max Activating Token Index: 574