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

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

Neuron 1662 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1286118 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1184939 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1193900 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1769. Min Act: -0.0000

Data Index: 428272 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1528. Min Act: -0.0000

Data Index: 743161 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1608. Min Act: -0.0000

Data Index: 669292 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1551. Min Act: -0.0000

Data Index: 775122 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1242577 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1488. Min Act: -0.0000

Data Index: 105632 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1154367 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1481. Min Act: -0.0000

Data Index: 202257 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1065972 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1555. Min Act: -0.0000

Data Index: 406839 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1450. Min Act: -0.0000

Data Index: 812372 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1285365 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1364. Min Act: -0.0000

Data Index: 198293 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1403. Min Act: -0.0000

Data Index: 865711 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1456. Min Act: -0.0000

Data Index: 161211 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1403. Min Act: -0.0000

Data Index: 840657 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.1940. Min Range: -0.1940

Max Act: 0.1447. Min Act: -0.0000

Data Index: 245170 (C4 (Web Text))

Max Activating Token Index: 332