Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 492 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3922. Min Range: -3.3922

Max Act: 3.3064. Min Act: -0.0000

Data Index: 157928 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 3.3922. Min Range: -3.3922

Max Act: 3.2809. Min Act: -0.0000

Data Index: 710638 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 3.3922. Min Range: -3.3922

Max Act: 3.2525. Min Act: -0.0000

Data Index: 1319146 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 3.3922. Min Range: -3.3922

Max Act: 3.3922. Min Act: -0.0000

Data Index: 361878 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 3.3922. Min Range: -3.3922

Max Act: 3.1237. Min Act: -0.0000

Data Index: 1005170 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.9674. Min Act: -0.0000

Data Index: 971033 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.8839. Min Act: -0.0000

Data Index: 1298204 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.9628. Min Act: -0.0000

Data Index: 26457 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.9811. Min Act: -0.0000

Data Index: 421082 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.6890. Min Act: -0.0000

Data Index: 333785 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.5479. Min Act: -0.0000

Data Index: 1255849 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.4580. Min Act: -0.0000

Data Index: 653878 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.4568. Min Act: -0.0000

Data Index: 107304 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.2361. Min Act: -0.0000

Data Index: 552744 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.3353. Min Act: -0.0000

Data Index: 1072067 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.2241. Min Act: -0.0000

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.3171. Min Act: -0.0000

Data Index: 163912 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.1116. Min Act: -0.0000

Data Index: 1080764 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.2383. Min Act: -0.0000

Data Index: 753962 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 3.3922. Min Range: -3.3922

Max Act: 2.3255. Min Act: -0.0000

Data Index: 149101 (C4 (Web Text))

Max Activating Token Index: 577