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

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

Neuron 1950 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.5403. Min Act: -0.1700

Data Index: 758241 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.5246. Min Act: -0.1700

Data Index: 1027495 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.5090. Min Act: -0.1700

Data Index: 419951 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4933. Min Act: -0.1700

Data Index: 196549 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.5090. Min Act: -0.1700

Data Index: 1147266 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4933. Min Act: -0.1700

Data Index: 1028918 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4933. Min Act: -0.1700

Data Index: 405016 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4933. Min Act: -0.1700

Data Index: 778390 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4776. Min Act: -0.1700

Data Index: 1069908 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4776. Min Act: -0.1700

Data Index: 1135873 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4619. Min Act: -0.1700

Data Index: 673632 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4619. Min Act: -0.1700

Data Index: 571059 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4933. Min Act: -0.1700

Data Index: 168123 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4619. Min Act: -0.1700

Data Index: 604686 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4776. Min Act: -0.1700

Data Index: 1024812 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4619. Min Act: -0.1700

Data Index: 567343 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4306. Min Act: -0.1700

Data Index: 245922 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4619. Min Act: -0.1700

Data Index: 788196 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4306. Min Act: -0.1700

Data Index: 93739 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4619. Min Act: -0.1700

Data Index: 866978 (C4 (Web Text))

Max Activating Token Index: 820