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

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

Neuron 1740 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: 5.6004. Min Range: -5.6004

Max Act: 5.6004. Min Act: -0.1699

Data Index: 1007923 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.4754. Min Act: -0.1700

Data Index: 827225 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.4442. Min Act: -0.1700

Data Index: 778605 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.4442. Min Act: -0.1700

Data Index: 414287 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.3504. Min Act: -0.1700

Data Index: 58195 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.3817. Min Act: -0.1700

Data Index: 995003 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.3504. Min Act: -0.1700

Data Index: 1056225 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.3504. Min Act: -0.1700

Data Index: 691019 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.3192. Min Act: -0.1700

Data Index: 3812 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.4442. Min Act: -0.1700

Data Index: 364050 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.3192. Min Act: -0.1700

Data Index: 379916 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.3504. Min Act: -0.1700

Data Index: 195173 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.3504. Min Act: -0.1700

Data Index: 722942 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.3504. Min Act: -0.1700

Data Index: 7730 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.2567. Min Act: -0.1700

Data Index: 1308646 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.2879. Min Act: -0.1700

Data Index: 1355809 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.2567. Min Act: -0.1700

Data Index: 876650 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.2254. Min Act: -0.1700

Data Index: 936147 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.2254. Min Act: -0.1700

Data Index: 1226197 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 5.6004. Min Range: -5.6004

Max Act: 5.2567. Min Act: -0.1700

Data Index: 613274 (C4 (Web Text))

Max Activating Token Index: 574