Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1321 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.3393. Min Act: -0.1700

Data Index: 1586496 (Python Code)

Max Activating Token Index: 390

Text #1

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.2450. Min Act: -0.1700

Data Index: 1655418 (Python Code)

Max Activating Token Index: 492

Text #2

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.1191. Min Act: -0.1700

Data Index: 1362193 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.1033. Min Act: -0.1700

Data Index: 1578711 (Python Code)

Max Activating Token Index: 704

Text #4

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.1033. Min Act: -0.1700

Data Index: 1647495 (Python Code)

Max Activating Token Index: 713

Text #5

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.1033. Min Act: -0.1700

Data Index: 1610383 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.1033. Min Act: -0.1700

Data Index: 1475966 (Python Code)

Max Activating Token Index: 234

Text #7

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1436219 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1520517 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1572397 (Python Code)

Max Activating Token Index: 713

Text #10

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1511789 (Python Code)

Max Activating Token Index: 824

Text #11

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1437812 (Python Code)

Max Activating Token Index: 755

Text #12

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1387441 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1387859 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1542829 (Python Code)

Max Activating Token Index: 672

Text #15

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1393334 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1594350 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1600878 (Python Code)

Max Activating Token Index: 988

Text #18

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1513167 (Python Code)

Max Activating Token Index: 273

Text #19

Max Range: 3.3393. Min Range: -3.3393

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1634349 (Python Code)

Max Activating Token Index: 544