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

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

Neuron 29 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.2513. Min Act: -0.1700

Data Index: 1319127 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.1888. Min Act: -0.1700

Data Index: 1224066 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.1575. Min Act: -0.1700

Data Index: 1225630 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.1888. Min Act: -0.1700

Data Index: 1123450 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.1263. Min Act: -0.1700

Data Index: 1282766 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.1888. Min Act: -0.1700

Data Index: 364691 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0950. Min Act: -0.1700

Data Index: 393543 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0950. Min Act: -0.1700

Data Index: 66462 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0950. Min Act: -0.1700

Data Index: 866685 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0638. Min Act: -0.1700

Data Index: 1135311 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0013. Min Act: -0.1700

Data Index: 66495 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0013. Min Act: -0.1700

Data Index: 561697 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0950. Min Act: -0.1700

Data Index: 1340644 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0638. Min Act: -0.1700

Data Index: 670423 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0325. Min Act: -0.1700

Data Index: 840621 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0325. Min Act: -0.1700

Data Index: 1108767 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 5.2513. Min Range: -5.2513

Max Act: 4.9388. Min Act: -0.1700

Data Index: 1029887 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 5.2513. Min Range: -5.2513

Max Act: 5.0013. Min Act: -0.1700

Data Index: 1307889 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 5.2513. Min Range: -5.2513

Max Act: 4.9700. Min Act: -0.1700

Data Index: 883604 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 5.2513. Min Range: -5.2513

Max Act: 4.9075. Min Act: -0.1700

Data Index: 511973 (C4 (Web Text))

Max Activating Token Index: 589