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

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

Neuron 4272 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1163157 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1665. Min Act: -0.0001

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1664. Min Act: -0.0001

Data Index: 722012 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1543. Min Act: -0.0001

Data Index: 1118502 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1670. Min Act: -0.0001

Data Index: 176269 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1612. Min Act: -0.0001

Data Index: 146209 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1113960 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1295517 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1566. Min Act: -0.0001

Data Index: 114281 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1309900 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1182530 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1337. Min Act: -0.0000

Data Index: 534729 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1420. Min Act: -0.0001

Data Index: 131273 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1052709 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1383. Min Act: -0.0000

Data Index: 374055 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1341. Min Act: -0.0000

Data Index: 288310 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1284. Min Act: -0.0000

Data Index: 553715 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1256786 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1572808 (Python Code)

Max Activating Token Index: 933

Text #19

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1346. Min Act: -0.0000

Data Index: 173695 (C4 (Web Text))

Max Activating Token Index: 168