Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1998. Min Act: -0.0000

Data Index: 259830 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1930. Min Act: -0.0000

Data Index: 770216 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1845. Min Act: -0.0000

Data Index: 695990 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1778. Min Act: -0.0000

Data Index: 780639 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1752. Min Act: -0.0000

Data Index: 387544 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1629. Min Act: -0.0000

Data Index: 570713 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1655. Min Act: -0.0000

Data Index: 140426 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1710. Min Act: -0.0000

Data Index: 186382 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1556. Min Act: -0.0000

Data Index: 634032 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1656. Min Act: -0.0000

Data Index: 769233 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1589. Min Act: -0.0000

Data Index: 56950 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1012872 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1558. Min Act: -0.0000

Data Index: 112054 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1177123 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1523. Min Act: -0.0000

Data Index: 241682 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1512. Min Act: -0.0000

Data Index: 812663 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1505. Min Act: -0.0000

Data Index: 243203 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1050430 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1450. Min Act: -0.0000

Data Index: 543937 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1498. Min Act: -0.0000

Data Index: 137077 (C4 (Web Text))

Max Activating Token Index: 974