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

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

Neuron 3725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1636. Min Act: -0.0000

Data Index: 283023 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1165655 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1737. Min Act: -0.0000

Data Index: 526436 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1538. Min Act: -0.0000

Data Index: 595458 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1455. Min Act: -0.0000

Data Index: 32688 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1593. Min Act: -0.0000

Data Index: 748042 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1461. Min Act: -0.0000

Data Index: 171457 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1118910 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1466. Min Act: -0.0000

Data Index: 794686 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1457. Min Act: -0.0000

Data Index: 853602 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1360. Min Act: -0.0000

Data Index: 740794 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1282. Min Act: -0.0000

Data Index: 340532 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1471. Min Act: -0.0000

Data Index: 445506 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1410. Min Act: -0.0000

Data Index: 352340 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1376. Min Act: -0.0000

Data Index: 674298 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1436. Min Act: -0.0000

Data Index: 868104 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1403. Min Act: -0.0000

Data Index: 634300 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1344. Min Act: -0.0000

Data Index: 839941 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1379. Min Act: -0.0000

Data Index: 182346 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1039302 (C4 (Web Text))

Max Activating Token Index: 49