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

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

Neuron 4689 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1730. Min Act: -0.0000

Data Index: 832130 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1768. Min Act: -0.0000

Data Index: 144986 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1463. Min Act: -0.0000

Data Index: 17461 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1086042 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1560. Min Act: -0.0000

Data Index: 296653 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1407. Min Act: -0.0000

Data Index: 665664 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1522. Min Act: -0.0000

Data Index: 177825 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1439. Min Act: -0.0000

Data Index: 412873 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1447. Min Act: -0.0000

Data Index: 43473 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1565. Min Act: -0.0000

Data Index: 719239 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1369. Min Act: -0.0000

Data Index: 203020 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1412. Min Act: -0.0000

Data Index: 961120 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1511. Min Act: -0.0000

Data Index: 362566 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1306471 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1295. Min Act: -0.0000

Data Index: 91298 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1388. Min Act: -0.0000

Data Index: 335544 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1380. Min Act: -0.0000

Data Index: 544475 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1362. Min Act: -0.0000

Data Index: 308037 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1471. Min Act: -0.0000

Data Index: 404636 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1305. Min Act: -0.0000

Data Index: 992051 (C4 (Web Text))

Max Activating Token Index: 955