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

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

Neuron 3117 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.9920. Min Act: -0.0000

Data Index: 132782 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.9092. Min Act: -0.0000

Data Index: 195533 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.8396. Min Act: -0.0001

Data Index: 70732 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7765. Min Act: -0.0001

Data Index: 182241 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.8137. Min Act: -0.0000

Data Index: 353475 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7622. Min Act: -0.0001

Data Index: 915720 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7557. Min Act: -0.0000

Data Index: 557792 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7142. Min Act: -0.0000

Data Index: 550737 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7388. Min Act: -0.0001

Data Index: 400371 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6543. Min Act: -0.0001

Data Index: 968520 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6543. Min Act: -0.0001

Data Index: 956097 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6761. Min Act: -0.0000

Data Index: 906443 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6414. Min Act: -0.0000

Data Index: 825681 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6774. Min Act: -0.0000

Data Index: 518254 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6435. Min Act: -0.0000

Data Index: 87666 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6442. Min Act: -0.0001

Data Index: 517806 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6392. Min Act: -0.0001

Data Index: 1066837 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6105. Min Act: 0.0001

Data Index: 652821 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6855. Min Act: -0.0000

Data Index: 267671 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.5973. Min Act: -0.0001

Data Index: 866020 (C4 (Web Text))

Max Activating Token Index: 326