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

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

Neuron 1392 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1702. Min Range: -5.1702

Max Act: 5.1702. Min Act: -0.1700

Data Index: 1530655 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 5.1702. Min Range: -5.1702

Max Act: 5.0920. Min Act: -0.1700

Data Index: 431728 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.9670. Min Act: -0.1700

Data Index: 1558988 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.9202. Min Act: -0.1700

Data Index: 1639570 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.8577. Min Act: -0.1700

Data Index: 1472494 (Python Code)

Max Activating Token Index: 451

Text #5

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.9358. Min Act: -0.1700

Data Index: 1482039 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.8264. Min Act: -0.1700

Data Index: 1421811 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.7952. Min Act: -0.1700

Data Index: 1635104 (Python Code)

Max Activating Token Index: 777

Text #8

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.7483. Min Act: -0.1700

Data Index: 1533169 (Python Code)

Max Activating Token Index: 1011

Text #9

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.8108. Min Act: -0.1700

Data Index: 1591946 (Python Code)

Max Activating Token Index: 887

Text #10

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.8420. Min Act: -0.1700

Data Index: 1598307 (Python Code)

Max Activating Token Index: 766

Text #11

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.8108. Min Act: -0.1700

Data Index: 1563343 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.8108. Min Act: -0.1700

Data Index: 1598360 (Python Code)

Max Activating Token Index: 1021

Text #13

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.8108. Min Act: -0.1700

Data Index: 1437784 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.7795. Min Act: -0.1700

Data Index: 1650935 (Python Code)

Max Activating Token Index: 908

Text #15

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.7639. Min Act: -0.1700

Data Index: 1361157 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.8108. Min Act: -0.1700

Data Index: 1601329 (Python Code)

Max Activating Token Index: 181

Text #17

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.8108. Min Act: -0.1700

Data Index: 1544085 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.7639. Min Act: -0.1700

Data Index: 1521622 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 5.1702. Min Range: -5.1702

Max Act: 4.7639. Min Act: -0.1700

Data Index: 1401467 (Python Code)

Max Activating Token Index: 1015