Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1618 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.1566. Min Range: -4.1566

Max Act: 4.1566. Min Act: -0.1700

Data Index: 1544109 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 4.1566. Min Range: -4.1566

Max Act: 4.1253. Min Act: -0.1552

Data Index: 1479434 (Python Code)

Max Activating Token Index: 904

Text #2

Max Range: 4.1566. Min Range: -4.1566

Max Act: 4.0315. Min Act: -0.1700

Data Index: 1565755 (Python Code)

Max Activating Token Index: 888

Text #3

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.9690. Min Act: -0.1700

Data Index: 1519923 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.9690. Min Act: -0.1698

Data Index: 1398167 (Python Code)

Max Activating Token Index: 746

Text #5

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.9064. Min Act: -0.1700

Data Index: 1422068 (Python Code)

Max Activating Token Index: 531

Text #6

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.9377. Min Act: -0.1700

Data Index: 1546205 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.9690. Min Act: -0.1700

Data Index: 1419517 (Python Code)

Max Activating Token Index: 964

Text #8

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.9377. Min Act: -0.1237

Data Index: 1491261 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.9064. Min Act: -0.1685

Data Index: 1441888 (Python Code)

Max Activating Token Index: 947

Text #10

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.9064. Min Act: -0.1700

Data Index: 1645011 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.8752. Min Act: -0.1700

Data Index: 1434711 (Python Code)

Max Activating Token Index: 986

Text #12

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.8439. Min Act: -0.1697

Data Index: 1649879 (Python Code)

Max Activating Token Index: 211

Text #13

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.8439. Min Act: -0.1700

Data Index: 1529134 (Python Code)

Max Activating Token Index: 872

Text #14

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.8439. Min Act: -0.1700

Data Index: 1490577 (Python Code)

Max Activating Token Index: 515

Text #15

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.8439. Min Act: -0.1700

Data Index: 1450918 (Python Code)

Max Activating Token Index: 1012

Text #16

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.8126. Min Act: -0.1700

Data Index: 1542377 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.8126. Min Act: -0.1682

Data Index: 1467945 (Python Code)

Max Activating Token Index: 888

Text #18

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.7813. Min Act: -0.1699

Data Index: 1457784 (Python Code)

Max Activating Token Index: 873

Text #19

Max Range: 4.1566. Min Range: -4.1566

Max Act: 3.7813. Min Act: -0.1699

Data Index: 1435427 (Python Code)

Max Activating Token Index: 320