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

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

Neuron 2501 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: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0001

Data Index: 162301 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0377. Min Act: -0.0001

Data Index: 555919 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0375. Min Act: -0.0001

Data Index: 781820 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1183261 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0371. Min Act: -0.0001

Data Index: 742246 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1348151 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0397. Min Act: -0.0001

Data Index: 656136 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1334794 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0351. Min Act: -0.0002

Data Index: 959229 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0336. Min Act: -0.0001

Data Index: 615095 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1182623 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0301. Min Act: -0.0001

Data Index: 102301 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0319. Min Act: -0.0001

Data Index: 420776 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0323. Min Act: -0.0001

Data Index: 928455 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0313. Min Act: -0.0001

Data Index: 496122 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0318. Min Act: -0.0001

Data Index: 707754 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0311. Min Act: -0.0001

Data Index: 593537 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0317. Min Act: -0.0001

Data Index: 559835 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0321. Min Act: -0.0001

Data Index: 520523 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0332. Min Act: -0.0001

Data Index: 919185 (C4 (Web Text))

Max Activating Token Index: 274