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

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

Neuron 4025 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.4300. Min Act: -0.0001

Data Index: 961899 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.0583. Min Act: -0.0001

Data Index: 163912 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1006. Min Act: -0.0001

Data Index: 653878 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.9536. Min Act: -0.0001

Data Index: 1359073 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.9253. Min Act: -0.0001

Data Index: 501688 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.9126. Min Act: -0.0001

Data Index: 149101 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8892. Min Act: -0.0001

Data Index: 171797 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.9074. Min Act: -0.0001

Data Index: 118020 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.9299. Min Act: -0.0001

Data Index: 600567 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8850. Min Act: -0.0001

Data Index: 351745 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8444. Min Act: -0.0001

Data Index: 833495 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8587. Min Act: -0.0001

Data Index: 79837 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8827. Min Act: -0.0001

Data Index: 801127 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8928. Min Act: -0.0001

Data Index: 704475 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.7777. Min Act: -0.0001

Data Index: 94154 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8034. Min Act: -0.0001

Data Index: 205712 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8003. Min Act: -0.0001

Data Index: 527352 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8503. Min Act: -0.0001

Data Index: 523604 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8187. Min Act: -0.0001

Data Index: 478922 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.4300. Min Range: -1.4300

Max Act: 0.8166. Min Act: -0.0001

Data Index: 98063 (C4 (Web Text))

Max Activating Token Index: 979