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

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

Neuron 3404 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: 0.1752. Min Range: -0.1752

Max Act: 0.1752. Min Act: -0.0000

Data Index: 366884 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1751. Min Act: -0.0000

Data Index: 134590 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1532. Min Act: -0.0000

Data Index: 686877 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1635. Min Act: -0.0000

Data Index: 630575 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1451. Min Act: -0.0000

Data Index: 54664 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1491. Min Act: -0.0000

Data Index: 253898 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1601. Min Act: -0.0000

Data Index: 331009 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1529. Min Act: -0.0000

Data Index: 382267 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1195133 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1441. Min Act: -0.0000

Data Index: 814461 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1480. Min Act: -0.0000

Data Index: 549478 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1024300 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1362. Min Act: -0.0000

Data Index: 61433 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1523. Min Act: -0.0000

Data Index: 264273 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1456. Min Act: -0.0000

Data Index: 555857 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1330. Min Act: -0.0000

Data Index: 674870 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1418. Min Act: -0.0000

Data Index: 58352 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1369. Min Act: -0.0000

Data Index: 65841 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1360. Min Act: -0.0000

Data Index: 930251 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1351. Min Act: -0.0000

Data Index: 837221 (C4 (Web Text))

Max Activating Token Index: 68