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

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

Neuron 382 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: 5.8679. Min Range: -5.8679

Max Act: 5.8679. Min Act: -0.1700

Data Index: 1625454 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.8366. Min Act: -0.1700

Data Index: 1531768 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.8366. Min Act: -0.1700

Data Index: 1384399 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.8366. Min Act: -0.1699

Data Index: 1530655 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7429. Min Act: -0.1700

Data Index: 1477286 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.8366. Min Act: -0.1700

Data Index: 1509489 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7741. Min Act: -0.1700

Data Index: 1643003 (Python Code)

Max Activating Token Index: 691

Text #7

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7741. Min Act: -0.1700

Data Index: 1570842 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7741. Min Act: -0.1700

Data Index: 1434441 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6804. Min Act: -0.1700

Data Index: 1628396 (Python Code)

Max Activating Token Index: 581

Text #10

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7429. Min Act: -0.1700

Data Index: 1437002 (Python Code)

Max Activating Token Index: 733

Text #11

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7116. Min Act: -0.1700

Data Index: 1585392 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7741. Min Act: -0.1700

Data Index: 1583959 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7429. Min Act: -0.1700

Data Index: 1500132 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.7741. Min Act: -0.1700

Data Index: 1526819 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6804. Min Act: -0.1700

Data Index: 1454027 (Python Code)

Max Activating Token Index: 441

Text #16

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.5866. Min Act: -0.1700

Data Index: 1423770 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6179. Min Act: -0.1700

Data Index: 1461850 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6804. Min Act: -0.1700

Data Index: 1579894 (Python Code)

Max Activating Token Index: 563

Text #19

Max Range: 5.8679. Min Range: -5.8679

Max Act: 5.6179. Min Act: -0.1700

Data Index: 1605430 (Python Code)

Max Activating Token Index: 620