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

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

Neuron 2610 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.7480. Min Act: -0.0001

Data Index: 620852 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.6608. Min Act: -0.0001

Data Index: 947577 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5629. Min Act: -0.0001

Data Index: 977272 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5115. Min Act: -0.0001

Data Index: 578000 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4468. Min Act: -0.0001

Data Index: 260077 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4798. Min Act: -0.0001

Data Index: 763137 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4993. Min Act: -0.0001

Data Index: 950829 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4516. Min Act: -0.0001

Data Index: 174456 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4830. Min Act: -0.0001

Data Index: 924321 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4849. Min Act: -0.0001

Data Index: 928358 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5226. Min Act: -0.0001

Data Index: 569900 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5576. Min Act: -0.0001

Data Index: 105688 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4719. Min Act: -0.0001

Data Index: 117295 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4676. Min Act: -0.0001

Data Index: 359115 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4257. Min Act: -0.0001

Data Index: 640639 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4689. Min Act: -0.0001

Data Index: 542503 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4580. Min Act: -0.0001

Data Index: 56261 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4115. Min Act: -0.0001

Data Index: 773379 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4250. Min Act: -0.0001

Data Index: 1260756 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5349. Min Act: -0.0001

Data Index: 1385929 (Python Code)

Max Activating Token Index: 880