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

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

Neuron 1630 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: 5.9857. Min Range: -5.9857

Max Act: 5.9857. Min Act: -0.1700

Data Index: 1248859 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.8920. Min Act: -0.1700

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.8920. Min Act: -0.1700

Data Index: 906519 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.8920. Min Act: -0.1700

Data Index: 516072 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.8920. Min Act: -0.1698

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.8920. Min Act: -0.1700

Data Index: 1304207 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.8607. Min Act: -0.1699

Data Index: 1316614 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.8295. Min Act: -0.1700

Data Index: 1325379 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.8295. Min Act: -0.1699

Data Index: 110253 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.7982. Min Act: -0.1700

Data Index: 864354 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.8295. Min Act: -0.1699

Data Index: 98929 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.7982. Min Act: -0.1699

Data Index: 872517 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.7670. Min Act: -0.1699

Data Index: 243381 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.7357. Min Act: -0.1700

Data Index: 82278 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.7045. Min Act: -0.1700

Data Index: 712177 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.7045. Min Act: -0.1697

Data Index: 924678 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.7045. Min Act: -0.1700

Data Index: 804677 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.7045. Min Act: -0.1700

Data Index: 922328 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.6732. Min Act: -0.1700

Data Index: 816699 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 5.9857. Min Range: -5.9857

Max Act: 5.6420. Min Act: -0.1700

Data Index: 83239 (C4 (Web Text))

Max Activating Token Index: 762