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

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

Neuron 4197 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: 2.4642. Min Range: -2.4642

Max Act: 2.4642. Min Act: -0.0002

Data Index: 972110 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 2.4642. Min Range: -2.4642

Max Act: 2.0932. Min Act: -0.0002

Data Index: 211837 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.9471. Min Act: -0.0002

Data Index: 553580 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.9151. Min Act: -0.0002

Data Index: 1007599 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.8230. Min Act: -0.0002

Data Index: 1069441 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.8004. Min Act: -0.0002

Data Index: 1057565 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.7559. Min Act: -0.0002

Data Index: 529754 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.7129. Min Act: -0.0003

Data Index: 1008986 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6919. Min Act: -0.0002

Data Index: 843683 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6807. Min Act: -0.0002

Data Index: 202980 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6823. Min Act: -0.0002

Data Index: 1003126 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6947. Min Act: -0.0002

Data Index: 127986 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6501. Min Act: -0.0002

Data Index: 234666 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6700. Min Act: -0.0002

Data Index: 309019 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6593. Min Act: -0.0003

Data Index: 1295131 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6644. Min Act: -0.0002

Data Index: 211671 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6623. Min Act: -0.0002

Data Index: 134618 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6387. Min Act: -0.0002

Data Index: 1287120 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6317. Min Act: -0.0002

Data Index: 1228179 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6462. Min Act: -0.0002

Data Index: 647463 (C4 (Web Text))

Max Activating Token Index: 465