Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2334 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.4744. Min Act: -0.0001

Data Index: 1066213 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.4169. Min Act: -0.0001

Data Index: 1076421 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.4103. Min Act: -0.0001

Data Index: 180594 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.3591. Min Act: -0.0000

Data Index: 771053 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.3128. Min Act: -0.0000

Data Index: 15508 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.2197. Min Act: -0.0000

Data Index: 333823 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1320443 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1776. Min Act: -0.0000

Data Index: 557235 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.2082. Min Act: -0.0001

Data Index: 731213 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.2342. Min Act: -0.0000

Data Index: 1269961 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1389. Min Act: -0.0001

Data Index: 787344 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1220870 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0966. Min Act: -0.0000

Data Index: 48066 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1359. Min Act: -0.0001

Data Index: 220745 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1642. Min Act: -0.0001

Data Index: 574738 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1698. Min Act: -0.0000

Data Index: 548019 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1259. Min Act: -0.0000

Data Index: 219453 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0957. Min Act: -0.0000

Data Index: 486583 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1504. Min Act: -0.0001

Data Index: 571060 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1500. Min Act: -0.0001

Data Index: 803994 (C4 (Web Text))

Max Activating Token Index: 987