Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3256 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2733. Min Act: -0.0001

Data Index: 991488 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2615. Min Act: -0.0001

Data Index: 707874 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2253. Min Act: -0.0001

Data Index: 75884 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2148. Min Act: -0.0001

Data Index: 76289 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2079. Min Act: -0.0001

Data Index: 307594 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2040. Min Act: -0.0001

Data Index: 222417 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2112. Min Act: -0.0001

Data Index: 808570 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1893. Min Act: -0.0001

Data Index: 1280334 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1818. Min Act: -0.0001

Data Index: 254013 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1688. Min Act: -0.0001

Data Index: 1116908 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1926. Min Act: -0.0000

Data Index: 312821 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1742. Min Act: -0.0001

Data Index: 631881 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1719. Min Act: -0.0001

Data Index: 872615 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1669. Min Act: -0.0001

Data Index: 700233 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1179724 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1517. Min Act: -0.0001

Data Index: 663450 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1469. Min Act: -0.0001

Data Index: 148751 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1539. Min Act: -0.0001

Data Index: 239713 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1269007 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1477. Min Act: -0.0001

Data Index: 589841 (C4 (Web Text))

Max Activating Token Index: 576