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

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

Neuron 4857 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: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0002

Data Index: 389517 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0622. Min Act: -0.0002

Data Index: 972276 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0621. Min Act: -0.0003

Data Index: 24742 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0622. Min Act: -0.0002

Data Index: 376888 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0603. Min Act: -0.0002

Data Index: 299045 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1235638 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1061095 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0592. Min Act: -0.0002

Data Index: 896759 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0590. Min Act: -0.0002

Data Index: 694106 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1054855 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0577. Min Act: -0.0002

Data Index: 864139 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0576. Min Act: -0.0002

Data Index: 714113 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0582. Min Act: -0.0002

Data Index: 3491 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0587. Min Act: -0.0002

Data Index: 663403 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0578. Min Act: -0.0003

Data Index: 903516 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0589. Min Act: -0.0002

Data Index: 481540 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0577. Min Act: -0.0002

Data Index: 701043 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0578. Min Act: -0.0002

Data Index: 433828 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0577. Min Act: -0.0002

Data Index: 366524 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0571. Min Act: -0.0002

Data Index: 402481 (C4 (Web Text))

Max Activating Token Index: 162