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

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

Neuron 261 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.6527. Min Act: -0.1700

Data Index: 1372290 (Python Code)

Max Activating Token Index: 955

Text #1

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.5588. Min Act: -0.1700

Data Index: 1587921 (Python Code)

Max Activating Token Index: 899

Text #2

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.5275. Min Act: -0.1700

Data Index: 1362467 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4961. Min Act: -0.1698

Data Index: 1529493 (Python Code)

Max Activating Token Index: 568

Text #4

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4961. Min Act: -0.1700

Data Index: 1619730 (Python Code)

Max Activating Token Index: 748

Text #5

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4805. Min Act: -0.1700

Data Index: 1409403 (Python Code)

Max Activating Token Index: 497

Text #6

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4805. Min Act: -0.1700

Data Index: 1650154 (Python Code)

Max Activating Token Index: 259

Text #7

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4805. Min Act: -0.1700

Data Index: 1380233 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4334. Min Act: -0.1700

Data Index: 1417141 (Python Code)

Max Activating Token Index: 448

Text #9

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4021. Min Act: -0.1700

Data Index: 1561227 (Python Code)

Max Activating Token Index: 294

Text #10

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.3550. Min Act: -0.1700

Data Index: 1489775 (Python Code)

Max Activating Token Index: 135

Text #11

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.3393. Min Act: -0.1700

Data Index: 1497194 (Python Code)

Max Activating Token Index: 918

Text #12

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.3079. Min Act: -0.1700

Data Index: 1616571 (Python Code)

Max Activating Token Index: 925

Text #13

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.3079. Min Act: -0.1700

Data Index: 1532845 (Python Code)

Max Activating Token Index: 441

Text #14

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.2922. Min Act: -0.1700

Data Index: 1511860 (Python Code)

Max Activating Token Index: 426

Text #15

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.2922. Min Act: -0.1700

Data Index: 1362129 (Python Code)

Max Activating Token Index: 969

Text #16

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.2765. Min Act: -0.1700

Data Index: 1369633 (Python Code)

Max Activating Token Index: 320

Text #17

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.2765. Min Act: -0.1700

Data Index: 1365965 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.2608. Min Act: -0.1700

Data Index: 1576632 (Python Code)

Max Activating Token Index: 839

Text #19

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.2608. Min Act: -0.1700

Data Index: 1436010 (Python Code)

Max Activating Token Index: 147