Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1756 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.0465. Min Range: -5.0465

Max Act: 5.0465. Min Act: -0.1699

Data Index: 1482780 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.9587. Min Act: -0.1700

Data Index: 1550683 (Python Code)

Max Activating Token Index: 352

Text #2

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8602. Min Act: -0.1700

Data Index: 1521014 (Python Code)

Max Activating Token Index: 917

Text #3

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8418. Min Act: -0.1700

Data Index: 1556571 (Python Code)

Max Activating Token Index: 727

Text #4

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8756. Min Act: -0.1700

Data Index: 1389372 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8651. Min Act: -0.1678

Data Index: 1402762 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8705. Min Act: -0.1700

Data Index: 1422374 (Python Code)

Max Activating Token Index: 625

Text #7

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8064. Min Act: -0.1700

Data Index: 1411296 (Python Code)

Max Activating Token Index: 575

Text #8

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8116. Min Act: -0.1700

Data Index: 1416248 (Python Code)

Max Activating Token Index: 87

Text #9

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7976. Min Act: -0.1699

Data Index: 1653500 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7946. Min Act: -0.1700

Data Index: 1457889 (Python Code)

Max Activating Token Index: 976

Text #11

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7455. Min Act: -0.1700

Data Index: 1508032 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7560. Min Act: -0.1700

Data Index: 1546563 (Python Code)

Max Activating Token Index: 627

Text #13

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7490. Min Act: -0.1700

Data Index: 1584512 (Python Code)

Max Activating Token Index: 390

Text #14

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7655. Min Act: -0.1700

Data Index: 1503636 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7169. Min Act: -0.1700

Data Index: 1442508 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.6870. Min Act: -0.1699

Data Index: 1391089 (Python Code)

Max Activating Token Index: 267

Text #17

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7018. Min Act: -0.1699

Data Index: 1556643 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.6855. Min Act: -0.1700

Data Index: 1584124 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7088. Min Act: -0.1673

Data Index: 1480589 (Python Code)

Max Activating Token Index: 233