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

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

Neuron 1850 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2236. Min Act: -0.0001

Data Index: 393615 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2246. Min Act: -0.0001

Data Index: 38392 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2000. Min Act: -0.0001

Data Index: 874246 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2014. Min Act: -0.0001

Data Index: 1019882 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1356272 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1657. Min Act: -0.0001

Data Index: 298443 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1489. Min Act: -0.0001

Data Index: 317161 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1463. Min Act: -0.0001

Data Index: 146411 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1564. Min Act: -0.0001

Data Index: 210660 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1458. Min Act: -0.0001

Data Index: 203730 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1434. Min Act: -0.0001

Data Index: 1191452 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1379. Min Act: -0.0001

Data Index: 583174 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1315413 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1579. Min Act: -0.0001

Data Index: 7826 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1418. Min Act: -0.0001

Data Index: 409110 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1630. Min Act: -0.0001

Data Index: 177484 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1382. Min Act: -0.0001

Data Index: 267306 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1051557 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1480. Min Act: -0.0001

Data Index: 572264 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1383. Min Act: -0.0001

Data Index: 833119 (C4 (Web Text))

Max Activating Token Index: 158