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

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

Neuron 3694 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5666. Min Act: -0.0002

Data Index: 377326 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5412. Min Act: -0.0001

Data Index: 118765 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5113. Min Act: -0.0001

Data Index: 325992 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5148. Min Act: -0.0001

Data Index: 1073877 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4873. Min Act: -0.0002

Data Index: 1094624 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5312. Min Act: -0.0001

Data Index: 423262 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4793. Min Act: -0.0001

Data Index: 528131 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4642. Min Act: -0.0002

Data Index: 1282269 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5141. Min Act: -0.0002

Data Index: 304317 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5051. Min Act: -0.0001

Data Index: 1139514 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5279. Min Act: -0.0001

Data Index: 671929 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4629. Min Act: -0.0001

Data Index: 513673 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4876. Min Act: -0.0001

Data Index: 52554 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5487. Min Act: -0.0002

Data Index: 980295 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5027. Min Act: -0.0002

Data Index: 843121 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4847. Min Act: -0.0001

Data Index: 1095619 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4841. Min Act: -0.0002

Data Index: 257050 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4301. Min Act: -0.0002

Data Index: 1043747 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4997. Min Act: -0.0001

Data Index: 689593 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5125. Min Act: -0.0001

Data Index: 11596 (C4 (Web Text))

Max Activating Token Index: 905