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

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

Neuron 1334 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.1937. Min Act: -0.0000

Data Index: 945661 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0550. Min Act: 0.0000

Data Index: 1031706 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.9487. Min Act: 0.0001

Data Index: 534665 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.9593. Min Act: 0.0001

Data Index: 761710 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.6497. Min Act: -0.0000

Data Index: 1213008 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.6224. Min Act: 0.0000

Data Index: 1126392 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.7048. Min Act: -0.0000

Data Index: 457662 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.6845. Min Act: 0.0001

Data Index: 552403 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.7455. Min Act: 0.0000

Data Index: 224334 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.6436. Min Act: -0.0000

Data Index: 325210 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.5298. Min Act: -0.0000

Data Index: 370908 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1149530 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.4865. Min Act: -0.0000

Data Index: 1189220 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.5638. Min Act: -0.0000

Data Index: 978778 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.4698. Min Act: 0.0001

Data Index: 1341319 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.4666. Min Act: 0.0000

Data Index: 449829 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.5482. Min Act: -0.0000

Data Index: 724971 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.4368. Min Act: -0.0000

Data Index: 1249756 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.5242. Min Act: -0.0000

Data Index: 838910 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 2.1937. Min Range: -2.1937

Max Act: 1.4110. Min Act: 0.0001

Data Index: 159845 (C4 (Web Text))

Max Activating Token Index: 288