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

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

Neuron 722 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9772. Min Act: -0.0003

Data Index: 822926 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9686. Min Act: -0.0002

Data Index: 185828 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9498. Min Act: -0.0003

Data Index: 538555 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9187. Min Act: -0.0002

Data Index: 650550 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8979. Min Act: -0.0002

Data Index: 436104 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9144. Min Act: -0.0002

Data Index: 793553 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9079. Min Act: -0.0002

Data Index: 1220560 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8859. Min Act: -0.0002

Data Index: 1240717 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9076. Min Act: -0.0002

Data Index: 1089058 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8767. Min Act: -0.0002

Data Index: 78814 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8912. Min Act: -0.0002

Data Index: 633870 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8648. Min Act: -0.0002

Data Index: 305676 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8784. Min Act: -0.0002

Data Index: 103684 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8632. Min Act: -0.0002

Data Index: 509912 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8689. Min Act: -0.0002

Data Index: 439252 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8696. Min Act: -0.0002

Data Index: 783051 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8679. Min Act: -0.0002

Data Index: 556747 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8559. Min Act: -0.0002

Data Index: 684424 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8516. Min Act: -0.0002

Data Index: 84304 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8466. Min Act: -0.0002

Data Index: 1323328 (C4 (Web Text))

Max Activating Token Index: 126