Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2530 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0370. Min Act: -0.0001

Data Index: 419912 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1266373 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0001

Data Index: 376442 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0313. Min Act: -0.0001

Data Index: 910227 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1069042 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1283201 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0294. Min Act: -0.0001

Data Index: 664028 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0275. Min Act: -0.0001

Data Index: 349722 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0296. Min Act: -0.0001

Data Index: 604976 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0285. Min Act: -0.0001

Data Index: 343261 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1009228 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0275. Min Act: -0.0001

Data Index: 261540 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0261. Min Act: -0.0001

Data Index: 581951 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0240. Min Act: -0.0001

Data Index: 788194 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0263. Min Act: -0.0001

Data Index: 564898 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0253. Min Act: -0.0001

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0219. Min Act: -0.0001

Data Index: 921719 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0237. Min Act: -0.0001

Data Index: 283010 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1318400 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1421179 (Python Code)

Max Activating Token Index: 903