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

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

Neuron 2582 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: 1.6008. Min Range: -1.6008

Max Act: 1.6008. Min Act: -0.0000

Data Index: 309937 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.6008. Min Range: -1.6008

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1084152 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 1.6008. Min Range: -1.6008

Max Act: 1.1264. Min Act: -0.0000

Data Index: 316682 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 1.6008. Min Range: -1.6008

Max Act: 1.0125. Min Act: -0.0000

Data Index: 487226 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.6008. Min Range: -1.6008

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1095617 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.9692. Min Act: -0.0000

Data Index: 773948 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.9612. Min Act: -0.0000

Data Index: 967045 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.9628. Min Act: -0.0000

Data Index: 825078 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1210561 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.9465. Min Act: -0.0000

Data Index: 350712 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.8603. Min Act: -0.0000

Data Index: 90771 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.9137. Min Act: -0.0000

Data Index: 729917 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1069585 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.8992. Min Act: -0.0000

Data Index: 246980 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.8664. Min Act: -0.0000

Data Index: 265954 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.8569. Min Act: -0.0000

Data Index: 651638 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.8295. Min Act: -0.0000

Data Index: 27832 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1146267 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.8402. Min Act: -0.0000

Data Index: 342979 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 1.6008. Min Range: -1.6008

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1103519 (C4 (Web Text))

Max Activating Token Index: 89