Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1958 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1836. Min Act: -0.0001

Data Index: 408780 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1523. Min Act: -0.0000

Data Index: 591345 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1311252 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1676. Min Act: -0.0000

Data Index: 774280 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1198522 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1174757 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1622. Min Act: -0.0000

Data Index: 68199 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1530. Min Act: -0.0001

Data Index: 654969 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1228555 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1350. Min Act: -0.0001

Data Index: 53908 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1428. Min Act: -0.0001

Data Index: 299391 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1430. Min Act: -0.0001

Data Index: 428322 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1435. Min Act: -0.0001

Data Index: 356520 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1070257 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1340. Min Act: -0.0000

Data Index: 929839 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1440. Min Act: -0.0001

Data Index: 562786 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1479. Min Act: -0.0001

Data Index: 254009 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1371. Min Act: -0.0001

Data Index: 652610 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1356. Min Act: -0.0001

Data Index: 286068 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1334430 (C4 (Web Text))

Max Activating Token Index: 907