Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5797 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.6614. Min Act: -0.0000

Data Index: 911961 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5791. Min Act: -0.0000

Data Index: 905399 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5368. Min Act: -0.0000

Data Index: 715448 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1172537 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1304542 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5226. Min Act: -0.0000

Data Index: 416182 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5173. Min Act: -0.0000

Data Index: 919924 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5003. Min Act: -0.0000

Data Index: 24012 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5141. Min Act: -0.0000

Data Index: 950256 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.5062. Min Act: -0.0000

Data Index: 421545 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4958. Min Act: -0.0000

Data Index: 773349 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4900. Min Act: -0.0000

Data Index: 642044 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4751. Min Act: -0.0000

Data Index: 73688 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4755. Min Act: -0.0000

Data Index: 108128 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4898. Min Act: -0.0000

Data Index: 275983 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4706. Min Act: 0.0000

Data Index: 519864 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4629. Min Act: 0.0000

Data Index: 765749 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4498. Min Act: -0.0000

Data Index: 531416 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1336378 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.6614. Min Range: -0.6614

Max Act: 0.4588. Min Act: -0.0000

Data Index: 894305 (C4 (Web Text))

Max Activating Token Index: 711