Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1757 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1561906 (Python Code)

Max Activating Token Index: 255

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1289368 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1564689 (Python Code)

Max Activating Token Index: 278

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1373241 (Python Code)

Max Activating Token Index: 526

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1455390 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1375411 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1693. Min Act: -0.0001

Data Index: 1445027 (Python Code)

Max Activating Token Index: 88

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1555209 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1651220 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1624. Min Act: -0.0001

Data Index: 1407072 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1641297 (Python Code)

Max Activating Token Index: 997

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1631110 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1643640 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1511711 (Python Code)

Max Activating Token Index: 602

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1646168 (Python Code)

Max Activating Token Index: 455

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1492451 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1504823 (Python Code)

Max Activating Token Index: 598

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1399232 (Python Code)

Max Activating Token Index: 907

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1371380 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1548435 (Python Code)

Max Activating Token Index: 690