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

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

Neuron 4814 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0349. Min Act: -0.0000

Data Index: 658462 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1160331 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0321. Min Act: -0.0000

Data Index: 172537 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0294. Min Act: -0.0000

Data Index: 516592 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0303. Min Act: -0.0000

Data Index: 522438 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0317. Min Act: -0.0000

Data Index: 424860 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0300. Min Act: -0.0000

Data Index: 202607 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0268. Min Act: -0.0000

Data Index: 733502 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0286. Min Act: -0.0000

Data Index: 494452 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0278. Min Act: -0.0000

Data Index: 614887 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0256. Min Act: -0.0000

Data Index: 698557 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0280. Min Act: -0.0000

Data Index: 575158 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0245. Min Act: -0.0000

Data Index: 917016 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0262. Min Act: -0.0001

Data Index: 500821 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0267. Min Act: -0.0000

Data Index: 864611 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0304. Min Act: -0.0000

Data Index: 640152 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0250. Min Act: -0.0000

Data Index: 418949 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0220. Min Act: -0.0000

Data Index: 217203 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0249. Min Act: -0.0000

Data Index: 282657 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0246. Min Act: -0.0000

Data Index: 813306 (C4 (Web Text))

Max Activating Token Index: 494