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

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

Neuron 111 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: 4.0508. Min Range: -4.0508

Max Act: 4.0508. Min Act: -0.1700

Data Index: 1615979 (Python Code)

Max Activating Token Index: 471

Text #1

Max Range: 4.0508. Min Range: -4.0508

Max Act: 4.0508. Min Act: -0.1700

Data Index: 1627432 (Python Code)

Max Activating Token Index: 756

Text #2

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.9570. Min Act: -0.1698

Data Index: 1599507 (Python Code)

Max Activating Token Index: 598

Text #3

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.9257. Min Act: -0.1700

Data Index: 1369834 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.9257. Min Act: -0.1700

Data Index: 1537521 (Python Code)

Max Activating Token Index: 400

Text #5

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.9257. Min Act: -0.1695

Data Index: 1436303 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.9414. Min Act: -0.1684

Data Index: 1404364 (Python Code)

Max Activating Token Index: 526

Text #7

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.9101. Min Act: -0.1668

Data Index: 1603888 (Python Code)

Max Activating Token Index: 759

Text #8

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8945. Min Act: -0.0433

Data Index: 1418763 (Python Code)

Max Activating Token Index: 998

Text #9

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.9101. Min Act: -0.1699

Data Index: 1570495 (Python Code)

Max Activating Token Index: 727

Text #10

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8945. Min Act: -0.1691

Data Index: 1366751 (Python Code)

Max Activating Token Index: 897

Text #11

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8476. Min Act: -0.1689

Data Index: 1502582 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8476. Min Act: -0.1681

Data Index: 1491693 (Python Code)

Max Activating Token Index: 881

Text #13

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8319. Min Act: -0.1677

Data Index: 1390117 (Python Code)

Max Activating Token Index: 838

Text #14

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8632. Min Act: -0.1699

Data Index: 1440152 (Python Code)

Max Activating Token Index: 479

Text #15

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8476. Min Act: -0.1700

Data Index: 1511495 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8319. Min Act: -0.1427

Data Index: 165735 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8319. Min Act: -0.1700

Data Index: 1444472 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.8163. Min Act: -0.1699

Data Index: 1491907 (Python Code)

Max Activating Token Index: 760

Text #19

Max Range: 4.0508. Min Range: -4.0508

Max Act: 3.7850. Min Act: -0.1684

Data Index: 1384312 (Python Code)

Max Activating Token Index: 956