Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1412 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.2137. Min Act: -0.0000

Data Index: 221251 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1585. Min Act: -0.0000

Data Index: 435955 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1716. Min Act: -0.0000

Data Index: 864371 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1767. Min Act: -0.0000

Data Index: 185580 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1287105 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1625. Min Act: -0.0000

Data Index: 56958 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1473. Min Act: -0.0000

Data Index: 207255 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1259760 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1451. Min Act: -0.0000

Data Index: 379982 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1253324 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1415. Min Act: -0.0000

Data Index: 290236 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1350. Min Act: -0.0000

Data Index: 204210 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1296. Min Act: -0.0000

Data Index: 135382 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1343903 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1219. Min Act: -0.0000

Data Index: 255202 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1377. Min Act: -0.0000

Data Index: 34754 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1310. Min Act: -0.0000

Data Index: 200653 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1251774 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1278. Min Act: -0.0000

Data Index: 793102 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1223. Min Act: -0.0000

Data Index: 727470 (C4 (Web Text))

Max Activating Token Index: 349