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

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

Neuron 329 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6217. Min Act: -0.0001

Data Index: 779941 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5716. Min Act: -0.0001

Data Index: 1357930 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6218. Min Act: -0.0001

Data Index: 380110 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5526. Min Act: -0.0001

Data Index: 1092822 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5414. Min Act: -0.0001

Data Index: 1107689 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5135. Min Act: -0.0001

Data Index: 1014292 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5125. Min Act: -0.0001

Data Index: 418598 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4986. Min Act: -0.0001

Data Index: 411794 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4891. Min Act: -0.0001

Data Index: 788149 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5064. Min Act: -0.0001

Data Index: 316422 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4811. Min Act: -0.0001

Data Index: 1166080 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4811. Min Act: -0.0001

Data Index: 1014786 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4933. Min Act: -0.0001

Data Index: 751738 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4693. Min Act: -0.0001

Data Index: 157899 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4906. Min Act: -0.0001

Data Index: 1194459 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4902. Min Act: -0.0001

Data Index: 291525 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4372. Min Act: -0.0001

Data Index: 613743 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4691. Min Act: -0.0001

Data Index: 899020 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4529. Min Act: -0.0001

Data Index: 753770 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4422. Min Act: -0.0001

Data Index: 1070902 (C4 (Web Text))

Max Activating Token Index: 734