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

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

Neuron 2421 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1285259 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1496. Min Act: -0.0001

Data Index: 617512 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1537. Min Act: -0.0001

Data Index: 199731 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1459. Min Act: -0.0001

Data Index: 917731 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1439. Min Act: -0.0001

Data Index: 283092 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1438. Min Act: -0.0001

Data Index: 560396 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1479. Min Act: -0.0001

Data Index: 209165 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1474. Min Act: -0.0001

Data Index: 453870 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1461. Min Act: -0.0001

Data Index: 981039 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1458. Min Act: -0.0001

Data Index: 915551 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1433. Min Act: -0.0001

Data Index: 958478 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1313853 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1361. Min Act: -0.0001

Data Index: 157470 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1396. Min Act: -0.0001

Data Index: 110673 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1295. Min Act: -0.0001

Data Index: 38140 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1319. Min Act: -0.0001

Data Index: 966645 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1153193 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1272. Min Act: -0.0001

Data Index: 724083 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1173. Min Act: -0.0001

Data Index: 920243 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1284. Min Act: -0.0001

Data Index: 415388 (C4 (Web Text))

Max Activating Token Index: 990