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

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

Neuron 5481 in Layer 1

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: 1.3507. Min Range: -1.3507

Max Act: 1.3507. Min Act: -0.0002

Data Index: 1369978 (Python Code)

Max Activating Token Index: 466

Text #1

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2947. Min Act: -0.0002

Data Index: 21715 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2194. Min Act: -0.0002

Data Index: 1011438 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1712. Min Act: -0.0002

Data Index: 1458752 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1820. Min Act: -0.0002

Data Index: 590483 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2096. Min Act: -0.0002

Data Index: 1437480 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2151. Min Act: -0.0002

Data Index: 1533095 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1594. Min Act: -0.0002

Data Index: 1533475 (Python Code)

Max Activating Token Index: 961

Text #8

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2014. Min Act: -0.0002

Data Index: 620754 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1652. Min Act: -0.0002

Data Index: 464293 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1626. Min Act: -0.0002

Data Index: 1576654 (Python Code)

Max Activating Token Index: 900

Text #11

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1634. Min Act: -0.0002

Data Index: 1209792 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1954. Min Act: -0.0002

Data Index: 253464 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1573. Min Act: -0.0002

Data Index: 384665 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1604. Min Act: -0.0002

Data Index: 1557832 (Python Code)

Max Activating Token Index: 1016

Text #15

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1729. Min Act: -0.0002

Data Index: 87826 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1678. Min Act: -0.0002

Data Index: 1614383 (Python Code)

Max Activating Token Index: 569

Text #17

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1290. Min Act: -0.0002

Data Index: 1379057 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1197. Min Act: -0.0002

Data Index: 120202 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.1325. Min Act: -0.0002

Data Index: 662960 (C4 (Web Text))

Max Activating Token Index: 176