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

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

Neuron 1600 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.4180. Min Act: -0.0000

Data Index: 500126 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9887. Min Act: -0.0000

Data Index: 617795 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.8732. Min Act: -0.0000

Data Index: 353958 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.8123. Min Act: -0.0000

Data Index: 884455 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.7917. Min Act: -0.0000

Data Index: 950342 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1009328 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.7883. Min Act: -0.0000

Data Index: 940426 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.7650. Min Act: -0.0000

Data Index: 969442 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.7111. Min Act: -0.0000

Data Index: 412215 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.7350. Min Act: -0.0000

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1096861 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1238138 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1169752 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.7131. Min Act: -0.0000

Data Index: 318796 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.6541. Min Act: -0.0000

Data Index: 48598 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1083090 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.6647. Min Act: -0.0000

Data Index: 753586 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.6788. Min Act: -0.0000

Data Index: 150500 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.6544. Min Act: -0.0000

Data Index: 333276 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1154210 (C4 (Web Text))

Max Activating Token Index: 957