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

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

Neuron 250 in Layer 0

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: 0.1869. Min Range: -0.1869

Max Act: 0.1861. Min Act: -0.0001

Data Index: 252392 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1869. Min Act: -0.0001

Data Index: 920947 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1816. Min Act: -0.0001

Data Index: 601187 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1730. Min Act: -0.0001

Data Index: 383516 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1729. Min Act: -0.0001

Data Index: 718001 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1656. Min Act: -0.0001

Data Index: 46068 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1643. Min Act: -0.0001

Data Index: 117747 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1638. Min Act: -0.0001

Data Index: 146713 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1638. Min Act: -0.0001

Data Index: 631497 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1547856 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1375085 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1595. Min Act: -0.0001

Data Index: 997815 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1608. Min Act: -0.0001

Data Index: 639177 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1416238 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1624. Min Act: -0.0001

Data Index: 566954 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1060484 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1599. Min Act: -0.0001

Data Index: 541696 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1574. Min Act: -0.0001

Data Index: 577826 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1354036 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1546. Min Act: -0.0001

Data Index: 1296630 (C4 (Web Text))

Max Activating Token Index: 349