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

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

Neuron 4814 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: 0.1818. Min Range: -0.1818

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1220074 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1755. Min Act: -0.0001

Data Index: 351217 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1692. Min Act: -0.0001

Data Index: 921610 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1727. Min Act: -0.0001

Data Index: 219992 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1634. Min Act: -0.0001

Data Index: 813173 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1654. Min Act: -0.0001

Data Index: 562007 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1689. Min Act: -0.0001

Data Index: 276344 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1602. Min Act: -0.0002

Data Index: 398094 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1593. Min Act: -0.0001

Data Index: 495316 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1610. Min Act: -0.0001

Data Index: 199335 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1563. Min Act: -0.0001

Data Index: 266788 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1069505 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1518. Min Act: -0.0001

Data Index: 1027858 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1275228 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1507. Min Act: -0.0002

Data Index: 1321061 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1478. Min Act: -0.0001

Data Index: 485607 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1026064 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1483. Min Act: -0.0001

Data Index: 72800 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1450. Min Act: -0.0001

Data Index: 477651 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1479. Min Act: -0.0002

Data Index: 1013568 (C4 (Web Text))

Max Activating Token Index: 390