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

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

Neuron 2190 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2224. Min Act: -0.0001

Data Index: 932766 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1784. Min Act: -0.0001

Data Index: 67983 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2264. Min Act: -0.0001

Data Index: 610048 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1767. Min Act: -0.0001

Data Index: 719321 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1712. Min Act: -0.0001

Data Index: 383865 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1672. Min Act: -0.0001

Data Index: 518707 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1721. Min Act: -0.0001

Data Index: 898486 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1660. Min Act: -0.0001

Data Index: 221248 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1571. Min Act: -0.0001

Data Index: 884163 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1562. Min Act: -0.0001

Data Index: 811543 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1482. Min Act: -0.0001

Data Index: 353993 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1543. Min Act: -0.0001

Data Index: 459684 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1431. Min Act: -0.0001

Data Index: 34536 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1392. Min Act: -0.0001

Data Index: 424251 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1510. Min Act: -0.0001

Data Index: 326146 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1472. Min Act: -0.0001

Data Index: 744575 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1491. Min Act: -0.0001

Data Index: 245097 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1264565 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1439. Min Act: -0.0001

Data Index: 241026 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1541. Min Act: -0.0001

Data Index: 320909 (C4 (Web Text))

Max Activating Token Index: 583