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

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

Neuron 2464 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1764. Min Act: -0.0002

Data Index: 1094267 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1738. Min Act: -0.0002

Data Index: 954110 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1646. Min Act: -0.0002

Data Index: 997299 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1578. Min Act: -0.0002

Data Index: 1064845 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1522. Min Act: -0.0002

Data Index: 386266 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1500. Min Act: -0.0002

Data Index: 1172646 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1537. Min Act: -0.0002

Data Index: 933746 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1511. Min Act: -0.0002

Data Index: 1292893 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1470. Min Act: -0.0002

Data Index: 581400 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1489. Min Act: -0.0002

Data Index: 1297905 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1537. Min Act: -0.0002

Data Index: 76827 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1460. Min Act: -0.0002

Data Index: 191726 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1490. Min Act: -0.0002

Data Index: 484796 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1494. Min Act: -0.0002

Data Index: 1285720 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1458. Min Act: -0.0002

Data Index: 480793 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1456. Min Act: -0.0002

Data Index: 62732 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1442. Min Act: -0.0002

Data Index: 1329928 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1251966 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1433. Min Act: -0.0002

Data Index: 840485 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1461. Min Act: -0.0002

Data Index: 79392 (C4 (Web Text))

Max Activating Token Index: 438