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

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

Neuron 1154 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.2894. Min Act: -0.0002

Data Index: 37182 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.2458. Min Act: -0.0001

Data Index: 675057 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1225730 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.2014. Min Act: -0.0001

Data Index: 648396 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1728. Min Act: -0.0001

Data Index: 47530 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1609480 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1594. Min Act: -0.0001

Data Index: 919934 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1567. Min Act: -0.0001

Data Index: 141840 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1333. Min Act: -0.0001

Data Index: 1360626 (Python Code)

Max Activating Token Index: 320

Text #9

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1507001 (Python Code)

Max Activating Token Index: 884

Text #10

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1177410 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1503. Min Act: -0.0001

Data Index: 387678 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1408. Min Act: -0.0001

Data Index: 769387 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1028532 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1403038 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1429471 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1231436 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1417451 (Python Code)

Max Activating Token Index: 709

Text #18

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1436. Min Act: -0.0001

Data Index: 509656 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.2894. Min Range: -0.2894

Max Act: 0.1420. Min Act: -0.0001

Data Index: 282553 (C4 (Web Text))

Max Activating Token Index: 913