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

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

Neuron 3907 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0308. Min Act: -0.0000

Data Index: 681546 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1011127 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0001

Data Index: 213598 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0322. Min Act: -0.0000

Data Index: 920381 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0288. Min Act: -0.0001

Data Index: 876838 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0288. Min Act: -0.0000

Data Index: 410866 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0277. Min Act: -0.0001

Data Index: 819768 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0300. Min Act: -0.0000

Data Index: 747715 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0256. Min Act: -0.0001

Data Index: 271471 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0276. Min Act: -0.0001

Data Index: 361002 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0255. Min Act: -0.0001

Data Index: 893759 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0273. Min Act: -0.0001

Data Index: 325703 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0256. Min Act: -0.0001

Data Index: 161809 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0241. Min Act: -0.0001

Data Index: 638662 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1240643 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0263. Min Act: -0.0000

Data Index: 250109 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1174165 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0257. Min Act: -0.0000

Data Index: 974387 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0291. Min Act: -0.0000

Data Index: 999062 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0259. Min Act: -0.0000

Data Index: 343434 (C4 (Web Text))

Max Activating Token Index: 800