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

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

Neuron 779 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: 3.6607. Min Range: -3.6607

Max Act: 3.6607. Min Act: -0.1700

Data Index: 1606173 (Python Code)

Max Activating Token Index: 652

Text #1

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.5668. Min Act: -0.1700

Data Index: 1627618 (Python Code)

Max Activating Token Index: 701

Text #2

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.4885. Min Act: -0.1700

Data Index: 1464818 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.4728. Min Act: -0.1700

Data Index: 1546439 (Python Code)

Max Activating Token Index: 759

Text #4

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.4571. Min Act: -0.1700

Data Index: 1427564 (Python Code)

Max Activating Token Index: 568

Text #5

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.4571. Min Act: -0.1683

Data Index: 1523517 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.4414. Min Act: -0.1699

Data Index: 1524310 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1150439 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1579092 (Python Code)

Max Activating Token Index: 371

Text #9

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1422942 (Python Code)

Max Activating Token Index: 937

Text #10

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3944. Min Act: -0.1699

Data Index: 1623034 (Python Code)

Max Activating Token Index: 269

Text #11

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3630. Min Act: -0.1700

Data Index: 1501602 (Python Code)

Max Activating Token Index: 618

Text #12

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3787. Min Act: -0.1691

Data Index: 1367188 (Python Code)

Max Activating Token Index: 826

Text #13

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3630. Min Act: -0.1695

Data Index: 1481894 (Python Code)

Max Activating Token Index: 865

Text #14

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3787. Min Act: -0.1698

Data Index: 1624630 (Python Code)

Max Activating Token Index: 541

Text #15

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3630. Min Act: -0.1700

Data Index: 1548802 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3630. Min Act: -0.1700

Data Index: 1611383 (Python Code)

Max Activating Token Index: 134

Text #17

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3159. Min Act: -0.1700

Data Index: 1619865 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3316. Min Act: -0.1689

Data Index: 1454456 (Python Code)

Max Activating Token Index: 615

Text #19

Max Range: 3.6607. Min Range: -3.6607

Max Act: 3.3630. Min Act: -0.1699

Data Index: 1418367 (Python Code)

Max Activating Token Index: 352