Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 703 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.2401. Min Act: -0.1700

Data Index: 282510 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.2088. Min Act: -0.1700

Data Index: 870493 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.1776. Min Act: -0.1700

Data Index: 977810 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.1776. Min Act: -0.1700

Data Index: 1354497 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.1463. Min Act: -0.1700

Data Index: 74703 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.0526. Min Act: -0.1700

Data Index: 186189 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.0838. Min Act: -0.1700

Data Index: 464537 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.0213. Min Act: -0.1700

Data Index: 9025 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.0526. Min Act: -0.1700

Data Index: 1230481 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.0526. Min Act: -0.1700

Data Index: 1181184 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.0526. Min Act: -0.1700

Data Index: 1246006 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.0213. Min Act: -0.1700

Data Index: 381922 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 5.2401. Min Range: -5.2401

Max Act: 4.9901. Min Act: -0.1700

Data Index: 96171 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.0213. Min Act: -0.1700

Data Index: 144870 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 5.2401. Min Range: -5.2401

Max Act: 4.9901. Min Act: -0.1700

Data Index: 724580 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 5.2401. Min Range: -5.2401

Max Act: 5.0213. Min Act: -0.1700

Data Index: 854235 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 5.2401. Min Range: -5.2401

Max Act: 4.9901. Min Act: -0.1700

Data Index: 451870 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 5.2401. Min Range: -5.2401

Max Act: 4.9588. Min Act: -0.1700

Data Index: 886738 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 5.2401. Min Range: -5.2401

Max Act: 4.8651. Min Act: -0.1700

Data Index: 1191503 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 5.2401. Min Range: -5.2401

Max Act: 4.9276. Min Act: -0.1700

Data Index: 527891 (C4 (Web Text))

Max Activating Token Index: 263