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

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

Neuron 4031 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5540. Min Range: -2.5540

Max Act: 2.5540. Min Act: -0.0000

Data Index: 114614 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.9863. Min Act: -0.0000

Data Index: 1276643 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.7673. Min Act: -0.0000

Data Index: 1011011 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.6714. Min Act: -0.0000

Data Index: 824372 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.3830. Min Act: -0.0000

Data Index: 55844 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.1654. Min Act: -0.0000

Data Index: 108031 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.2531. Min Act: -0.0000

Data Index: 1038355 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.1949. Min Act: -0.0000

Data Index: 829753 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.0521. Min Act: -0.0000

Data Index: 450637 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.1427. Min Act: -0.0000

Data Index: 123953 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.1195. Min Act: -0.0000

Data Index: 90684 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.0983. Min Act: -0.0000

Data Index: 599679 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.0160. Min Act: -0.0000

Data Index: 873838 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.0203. Min Act: -0.0000

Data Index: 337929 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.0173. Min Act: -0.0000

Data Index: 246574 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.0137. Min Act: -0.0000

Data Index: 699848 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 2.5540. Min Range: -2.5540

Max Act: 1.0380. Min Act: -0.0000

Data Index: 271749 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 2.5540. Min Range: -2.5540

Max Act: 0.9800. Min Act: -0.0000

Data Index: 872006 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 2.5540. Min Range: -2.5540

Max Act: 0.9510. Min Act: -0.0000

Data Index: 56617 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 2.5540. Min Range: -2.5540

Max Act: 0.9691. Min Act: -0.0000

Data Index: 588965 (C4 (Web Text))

Max Activating Token Index: 882