Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2046 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1767. Min Act: -0.0001

Data Index: 1327445 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1634. Min Act: -0.0001

Data Index: 325973 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1358847 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1033200 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1592. Min Act: -0.0001

Data Index: 472093 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1524. Min Act: -0.0001

Data Index: 965761 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1354224 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1492. Min Act: -0.0002

Data Index: 90685 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1139822 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1097031 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1265. Min Act: -0.0001

Data Index: 918122 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1354. Min Act: -0.0001

Data Index: 265097 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1321. Min Act: -0.0001

Data Index: 840449 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1024432 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1015192 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1329. Min Act: -0.0002

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1238. Min Act: -0.0001

Data Index: 717468 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1231. Min Act: -0.0001

Data Index: 875658 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1232. Min Act: -0.0001

Data Index: 759877 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1310. Min Act: -0.0001

Data Index: 427945 (C4 (Web Text))

Max Activating Token Index: 728