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

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

Neuron 1999 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: 3.2335. Min Range: -3.2335

Max Act: 3.2335. Min Act: -0.1700

Data Index: 1588926 (Python Code)

Max Activating Token Index: 792

Text #1

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.2335. Min Act: -0.1700

Data Index: 1441712 (Python Code)

Max Activating Token Index: 862

Text #2

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1551897 (Python Code)

Max Activating Token Index: 697

Text #3

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1639001 (Python Code)

Max Activating Token Index: 352

Text #4

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1597715 (Python Code)

Max Activating Token Index: 221

Text #5

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1564670 (Python Code)

Max Activating Token Index: 658

Text #6

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1863. Min Act: -0.1700

Data Index: 1398311 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.2178. Min Act: -0.1700

Data Index: 1650847 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1579625 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1555096 (Python Code)

Max Activating Token Index: 590

Text #10

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1463084 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1388214 (Python Code)

Max Activating Token Index: 960

Text #12

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1863. Min Act: -0.1700

Data Index: 1456166 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1863. Min Act: -0.1700

Data Index: 1460822 (Python Code)

Max Activating Token Index: 172

Text #14

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1558177 (Python Code)

Max Activating Token Index: 374

Text #15

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1428099 (Python Code)

Max Activating Token Index: 373

Text #16

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1548. Min Act: -0.1700

Data Index: 1411500 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1524609 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1436063 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1548. Min Act: -0.1700

Data Index: 1546716 (Python Code)

Max Activating Token Index: 713