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

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

Neuron 1110 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: 5.0827. Min Range: -5.0827

Max Act: 5.0827. Min Act: -0.1700

Data Index: 1130669 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 5.0827. Min Range: -5.0827

Max Act: 5.0515. Min Act: -0.1700

Data Index: 820012 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 5.0827. Min Range: -5.0827

Max Act: 5.0515. Min Act: -0.1700

Data Index: 439157 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 5.0827. Min Range: -5.0827

Max Act: 5.0202. Min Act: -0.1700

Data Index: 1179289 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 5.0827. Min Range: -5.0827

Max Act: 5.0202. Min Act: -0.1700

Data Index: 306736 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9265. Min Act: -0.1700

Data Index: 851417 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.8327. Min Act: -0.1700

Data Index: 293501 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9577. Min Act: -0.1700

Data Index: 190450 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9577. Min Act: -0.1700

Data Index: 301855 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.8640. Min Act: -0.1700

Data Index: 1350483 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9890. Min Act: -0.1700

Data Index: 1182682 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9890. Min Act: -0.1700

Data Index: 1190151 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9265. Min Act: -0.1700

Data Index: 1200495 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9577. Min Act: -0.1700

Data Index: 1061048 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.8952. Min Act: -0.1700

Data Index: 1136461 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.8640. Min Act: -0.1700

Data Index: 847125 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9265. Min Act: -0.1700

Data Index: 210938 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9265. Min Act: -0.1700

Data Index: 585987 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.9265. Min Act: -0.1700

Data Index: 422620 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 5.0827. Min Range: -5.0827

Max Act: 4.8327. Min Act: -0.1700

Data Index: 820999 (C4 (Web Text))

Max Activating Token Index: 248