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

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

Neuron 692 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: 0.9073. Min Range: -0.9073

Max Act: 0.9073. Min Act: -0.0001

Data Index: 1059936 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.8701. Min Act: -0.0001

Data Index: 1063679 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.7917. Min Act: -0.0001

Data Index: 487335 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.7533. Min Act: -0.0001

Data Index: 686676 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.7624. Min Act: -0.0002

Data Index: 522568 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.7102. Min Act: -0.0002

Data Index: 1050110 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6783. Min Act: -0.0001

Data Index: 901679 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.7003. Min Act: -0.0001

Data Index: 862769 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6712. Min Act: -0.0002

Data Index: 1172454 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6761. Min Act: -0.0002

Data Index: 457207 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6285. Min Act: -0.0001

Data Index: 318119 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6672. Min Act: -0.0002

Data Index: 1003616 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6487. Min Act: -0.0002

Data Index: 252339 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6785. Min Act: -0.0001

Data Index: 604020 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6103. Min Act: -0.0002

Data Index: 1001113 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5924. Min Act: -0.0002

Data Index: 407739 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6409. Min Act: -0.0002

Data Index: 265171 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5696. Min Act: -0.0002

Data Index: 702885 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5856. Min Act: -0.0002

Data Index: 864341 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6222. Min Act: -0.0002

Data Index: 731536 (C4 (Web Text))

Max Activating Token Index: 970