Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2272 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1726. Min Act: -0.0003

Data Index: 538169 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1586. Min Act: -0.0003

Data Index: 1021965 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1608. Min Act: -0.0003

Data Index: 76573 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1416. Min Act: -0.0003

Data Index: 138895 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1267. Min Act: -0.0003

Data Index: 708516 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1408. Min Act: -0.0003

Data Index: 485461 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1448. Min Act: -0.0003

Data Index: 1167352 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1430. Min Act: -0.0003

Data Index: 535560 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1416. Min Act: -0.0003

Data Index: 1264925 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1421. Min Act: -0.0003

Data Index: 608088 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1305. Min Act: -0.0003

Data Index: 100503 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1464. Min Act: -0.0003

Data Index: 656029 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1350. Min Act: -0.0003

Data Index: 361388 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1173. Min Act: -0.0003

Data Index: 1238544 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1339. Min Act: -0.0003

Data Index: 356104 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1338. Min Act: -0.0003

Data Index: 814952 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1362. Min Act: -0.0003

Data Index: 1092155 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1312. Min Act: -0.0003

Data Index: 419662 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1362. Min Act: -0.0003

Data Index: 775855 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1260. Min Act: -0.0003

Data Index: 668073 (C4 (Web Text))

Max Activating Token Index: 52