Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4398 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.5290. Min Range: -5.5290

Max Act: 5.5290. Min Act: -0.0000

Data Index: 327207 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 5.5290. Min Range: -5.5290

Max Act: 5.3236. Min Act: -0.0000

Data Index: 23758 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 5.5290. Min Range: -5.5290

Max Act: 5.1097. Min Act: -0.0000

Data Index: 1321472 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.9611. Min Act: -0.0000

Data Index: 1085943 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 5.5290. Min Range: -5.5290

Max Act: 5.1030. Min Act: -0.0000

Data Index: 1123457 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 5.5290. Min Range: -5.5290

Max Act: 5.0721. Min Act: -0.0000

Data Index: 1051038 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 5.5290. Min Range: -5.5290

Max Act: 5.0847. Min Act: -0.0000

Data Index: 1215138 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.9905. Min Act: -0.0000

Data Index: 953020 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.9137. Min Act: -0.0000

Data Index: 557200 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 5.5290. Min Range: -5.5290

Max Act: 5.0396. Min Act: -0.0000

Data Index: 1041701 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.5025. Min Act: -0.0000

Data Index: 1331595 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.2748. Min Act: -0.0000

Data Index: 1355578 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.2742. Min Act: -0.0000

Data Index: 1297153 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.1941. Min Act: -0.0000

Data Index: 349979 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 5.5290. Min Range: -5.5290

Max Act: 3.9871. Min Act: -0.0000

Data Index: 689954 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.1513. Min Act: -0.0000

Data Index: 429042 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.0992. Min Act: -0.0000

Data Index: 1000449 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.2167. Min Act: -0.0000

Data Index: 49584 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.2357. Min Act: -0.0000

Data Index: 824871 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 5.5290. Min Range: -5.5290

Max Act: 4.0641. Min Act: -0.0000

Data Index: 680807 (C4 (Web Text))

Max Activating Token Index: 625