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

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

Neuron 3980 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: 0.2058. Min Range: -0.2058

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1193992 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1062931 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1744. Min Act: -0.0000

Data Index: 285004 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1724. Min Act: -0.0000

Data Index: 997957 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1766. Min Act: -0.0000

Data Index: 604170 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1669. Min Act: -0.0000

Data Index: 432853 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1514. Min Act: -0.0000

Data Index: 957770 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1724. Min Act: -0.0000

Data Index: 378768 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1629. Min Act: -0.0000

Data Index: 116421 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1308486 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1571. Min Act: -0.0000

Data Index: 410239 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1547. Min Act: -0.0000

Data Index: 788883 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1431. Min Act: -0.0000

Data Index: 323516 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1495. Min Act: -0.0000

Data Index: 352151 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1450. Min Act: -0.0000

Data Index: 506142 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1170457 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1441. Min Act: -0.0000

Data Index: 98002 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1483. Min Act: -0.0000

Data Index: 974188 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1421. Min Act: -0.0000

Data Index: 897760 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1076571 (C4 (Web Text))

Max Activating Token Index: 88