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

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

Neuron 3567 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: 0.7676. Min Range: -0.7676

Max Act: 0.7676. Min Act: -0.0000

Data Index: 448331 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.6303. Min Act: -0.0001

Data Index: 593385 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.6366. Min Act: -0.0000

Data Index: 777389 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1348860 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.6097. Min Act: -0.0000

Data Index: 152143 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1297691 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5078. Min Act: -0.0001

Data Index: 1024362 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5441. Min Act: -0.0000

Data Index: 712598 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5118. Min Act: -0.0000

Data Index: 138849 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5244. Min Act: -0.0000

Data Index: 779017 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5601. Min Act: -0.0000

Data Index: 546896 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5166. Min Act: -0.0000

Data Index: 140370 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5103. Min Act: -0.0000

Data Index: 803527 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1282446 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.4958. Min Act: -0.0000

Data Index: 278107 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.4451. Min Act: -0.0000

Data Index: 256101 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.4989. Min Act: -0.0001

Data Index: 518288 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5273. Min Act: -0.0000

Data Index: 516559 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.4722. Min Act: -0.0000

Data Index: 653349 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5091. Min Act: -0.0001

Data Index: 1261423 (C4 (Web Text))

Max Activating Token Index: 16