Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1148 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1700. Min Act: -0.0004

Data Index: 1047407 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1553. Min Act: -0.0003

Data Index: 813334 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1534. Min Act: -0.0003

Data Index: 858036 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1447. Min Act: -0.0003

Data Index: 444931 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1502. Min Act: -0.0003

Data Index: 244927 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1472. Min Act: -0.0003

Data Index: 158741 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1469. Min Act: -0.0003

Data Index: 815435 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1470. Min Act: -0.0003

Data Index: 886376 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1450. Min Act: -0.0003

Data Index: 432214 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1467. Min Act: -0.0003

Data Index: 661709 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1455. Min Act: -0.0003

Data Index: 624714 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1465. Min Act: -0.0003

Data Index: 1326614 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1440. Min Act: -0.0002

Data Index: 1004236 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1440. Min Act: -0.0003

Data Index: 13994 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1436. Min Act: -0.0003

Data Index: 424885 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1399. Min Act: -0.0003

Data Index: 827964 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1438. Min Act: -0.0003

Data Index: 1173235 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1423. Min Act: -0.0003

Data Index: 383186 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1424. Min Act: -0.0004

Data Index: 1246845 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1372. Min Act: -0.0003

Data Index: 986578 (C4 (Web Text))

Max Activating Token Index: 225