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

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

Neuron 499 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: 5.5772. Min Range: -5.5772

Max Act: 5.5772. Min Act: -0.1700

Data Index: 336544 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.5147. Min Act: -0.1700

Data Index: 863816 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.5147. Min Act: -0.1699

Data Index: 1019797 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.4522. Min Act: -0.1700

Data Index: 1250053 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.4522. Min Act: -0.1700

Data Index: 161151 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.4210. Min Act: -0.1700

Data Index: 1122802 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.3585. Min Act: -0.1700

Data Index: 273160 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.3585. Min Act: -0.1700

Data Index: 1177226 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2960. Min Act: -0.1700

Data Index: 977903 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.3272. Min Act: -0.1700

Data Index: 909700 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2335. Min Act: -0.1700

Data Index: 633038 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2647. Min Act: -0.1700

Data Index: 1233640 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2647. Min Act: -0.1700

Data Index: 1276374 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2647. Min Act: -0.1700

Data Index: 787341 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2335. Min Act: -0.1700

Data Index: 49353 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2647. Min Act: -0.1700

Data Index: 1239448 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2335. Min Act: -0.1700

Data Index: 1209126 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2335. Min Act: -0.1700

Data Index: 1324414 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2647. Min Act: -0.1700

Data Index: 347727 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 5.5772. Min Range: -5.5772

Max Act: 5.2022. Min Act: -0.1696

Data Index: 1374042 (Python Code)

Max Activating Token Index: 400