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

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

Neuron 1659 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.9568. Min Act: -0.1700

Data Index: 20987 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.6756. Min Act: -0.1700

Data Index: 1162454 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.6443. Min Act: -0.1700

Data Index: 129313 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.6756. Min Act: -0.1700

Data Index: 1606600 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.6756. Min Act: -0.1700

Data Index: 1625043 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5818. Min Act: -0.1700

Data Index: 70036 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.6131. Min Act: -0.1700

Data Index: 37944 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.6131. Min Act: -0.1700

Data Index: 437031 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.6131. Min Act: -0.1700

Data Index: 627092 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5818. Min Act: -0.1700

Data Index: 1628325 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5818. Min Act: -0.1700

Data Index: 690858 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5818. Min Act: -0.1700

Data Index: 194832 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5506. Min Act: -0.1700

Data Index: 238677 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5193. Min Act: -0.1700

Data Index: 952633 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5818. Min Act: -0.1700

Data Index: 1335849 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5193. Min Act: -0.1700

Data Index: 619788 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5818. Min Act: -0.1700

Data Index: 933371 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5818. Min Act: -0.1700

Data Index: 1153891 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5193. Min Act: -0.1700

Data Index: 1368282 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 5.9568. Min Range: -5.9568

Max Act: 5.5193. Min Act: -0.1699

Data Index: 898612 (C4 (Web Text))

Max Activating Token Index: 480