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

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

Neuron 1981 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: 5.2318. Min Range: -5.2318

Max Act: 5.2005. Min Act: -0.1700

Data Index: 507690 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.2318. Min Act: -0.1700

Data Index: 1469975 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.1380. Min Act: -0.1700

Data Index: 1539511 (Python Code)

Max Activating Token Index: 432

Text #3

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.1693. Min Act: -0.1700

Data Index: 383479 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.2318. Min Act: -0.1700

Data Index: 1377168 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.2318. Min Act: -0.1700

Data Index: 1521179 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.2005. Min Act: -0.1700

Data Index: 1379931 (Python Code)

Max Activating Token Index: 273

Text #7

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.1693. Min Act: -0.1700

Data Index: 1531675 (Python Code)

Max Activating Token Index: 75

Text #8

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.1380. Min Act: -0.1700

Data Index: 1637241 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.0755. Min Act: -0.1700

Data Index: 1477589 (Python Code)

Max Activating Token Index: 694

Text #10

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.1380. Min Act: -0.1700

Data Index: 1602861 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.0755. Min Act: -0.1700

Data Index: 1571230 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.0130. Min Act: -0.1700

Data Index: 1375223 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.0755. Min Act: -0.1700

Data Index: 1472811 (Python Code)

Max Activating Token Index: 358

Text #14

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.0130. Min Act: -0.1700

Data Index: 1459115 (Python Code)

Max Activating Token Index: 410

Text #15

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.0130. Min Act: -0.1700

Data Index: 988629 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 5.2318. Min Range: -5.2318

Max Act: 4.9818. Min Act: -0.1700

Data Index: 1056993 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 5.2318. Min Range: -5.2318

Max Act: 4.9505. Min Act: -0.1700

Data Index: 1590775 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.0130. Min Act: -0.1700

Data Index: 1606105 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 5.2318. Min Range: -5.2318

Max Act: 5.0130. Min Act: -0.1700

Data Index: 1486621 (Python Code)

Max Activating Token Index: 209