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

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

Neuron 1764 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.5042. Min Act: -0.0000

Data Index: 92429 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4566. Min Act: -0.0000

Data Index: 351744 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1224832 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4478. Min Act: -0.0001

Data Index: 1292559 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1219161 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4087. Min Act: -0.0001

Data Index: 1131275 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3944. Min Act: -0.0000

Data Index: 867801 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3888. Min Act: -0.0000

Data Index: 419476 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3621. Min Act: -0.0000

Data Index: 238020 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3534. Min Act: -0.0001

Data Index: 595821 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3277. Min Act: -0.0000

Data Index: 55164 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1307726 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1343514 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3165. Min Act: -0.0001

Data Index: 92630 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3428. Min Act: -0.0001

Data Index: 887994 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3402. Min Act: -0.0000

Data Index: 134777 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3322. Min Act: -0.0000

Data Index: 705274 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1341345 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.2944. Min Act: -0.0000

Data Index: 3354 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.2894. Min Act: -0.0000

Data Index: 611699 (C4 (Web Text))

Max Activating Token Index: 735