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

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

Neuron 5954 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: 0.8974. Min Range: -0.8974

Max Act: 0.8974. Min Act: -0.0002

Data Index: 54777 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8867. Min Act: -0.0002

Data Index: 835135 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8502. Min Act: -0.0002

Data Index: 476184 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8406. Min Act: -0.0002

Data Index: 921599 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8235. Min Act: -0.0002

Data Index: 453445 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8187. Min Act: -0.0002

Data Index: 403418 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7933. Min Act: -0.0002

Data Index: 679375 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7917. Min Act: -0.0002

Data Index: 255974 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7816. Min Act: -0.0002

Data Index: 775325 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7668. Min Act: -0.0002

Data Index: 1140712 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7668. Min Act: -0.0002

Data Index: 917109 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7818. Min Act: -0.0002

Data Index: 684900 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7798. Min Act: -0.0002

Data Index: 679671 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7787. Min Act: -0.0002

Data Index: 1312954 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7734. Min Act: -0.0002

Data Index: 148522 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7576. Min Act: -0.0002

Data Index: 1194081 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7647. Min Act: -0.0002

Data Index: 514676 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7619. Min Act: -0.0003

Data Index: 547192 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7505. Min Act: -0.0002

Data Index: 841073 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7566. Min Act: -0.0002

Data Index: 784837 (C4 (Web Text))

Max Activating Token Index: 438