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

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

Neuron 1311 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: 0.1816. Min Range: -0.1816

Max Act: 0.1816. Min Act: -0.0000

Data Index: 554192 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1712. Min Act: -0.0000

Data Index: 679860 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1752. Min Act: -0.0000

Data Index: 383888 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1594. Min Act: -0.0000

Data Index: 378617 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1475. Min Act: -0.0000

Data Index: 44382 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1522. Min Act: -0.0000

Data Index: 642815 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1126600 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1535. Min Act: -0.0000

Data Index: 768153 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1390. Min Act: -0.0000

Data Index: 727228 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1373. Min Act: -0.0000

Data Index: 776323 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1206. Min Act: -0.0000

Data Index: 761947 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1323. Min Act: -0.0000

Data Index: 64932 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1361. Min Act: -0.0000

Data Index: 846476 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1269. Min Act: -0.0000

Data Index: 824571 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1304. Min Act: -0.0000

Data Index: 256344 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1350. Min Act: -0.0000

Data Index: 74566 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1345. Min Act: -0.0000

Data Index: 489483 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1246. Min Act: -0.0000

Data Index: 976655 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1197. Min Act: -0.0000

Data Index: 970353 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1297927 (C4 (Web Text))

Max Activating Token Index: 268