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

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

Neuron 2668 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4662. Min Range: -2.4662

Max Act: 2.4662. Min Act: -0.0000

Data Index: 469189 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.8800. Min Act: -0.0000

Data Index: 461937 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.9641. Min Act: -0.0000

Data Index: 7458 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.7223. Min Act: -0.0000

Data Index: 626561 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.7190. Min Act: -0.0000

Data Index: 1133744 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.5591. Min Act: -0.0000

Data Index: 657945 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6094. Min Act: -0.0000

Data Index: 1307718 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6667. Min Act: -0.0000

Data Index: 1233364 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6710. Min Act: -0.0000

Data Index: 717594 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.5804. Min Act: -0.0000

Data Index: 35039 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6484. Min Act: -0.0000

Data Index: 177816 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6609. Min Act: -0.0000

Data Index: 266839 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6532. Min Act: -0.0000

Data Index: 1226662 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6543. Min Act: -0.0000

Data Index: 389635 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.7467. Min Act: -0.0000

Data Index: 899881 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6339. Min Act: -0.0000

Data Index: 649549 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6293. Min Act: -0.0000

Data Index: 808173 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.6357. Min Act: -0.0000

Data Index: 844411 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.7094. Min Act: -0.0000

Data Index: 445862 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 2.4662. Min Range: -2.4662

Max Act: 1.5831. Min Act: -0.0000

Data Index: 465962 (C4 (Web Text))

Max Activating Token Index: 678