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

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

Neuron 191 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: 5.8868. Min Range: -5.8868

Max Act: 5.8868. Min Act: -0.1700

Data Index: 429226 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.6993. Min Act: -0.1700

Data Index: 154791 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.5743. Min Act: -0.1700

Data Index: 839710 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.5743. Min Act: -0.1692

Data Index: 1092288 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.5431. Min Act: -0.1700

Data Index: 33141 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.5431. Min Act: -0.1700

Data Index: 645418 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.5431. Min Act: -0.1700

Data Index: 412148 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.4806. Min Act: -0.1700

Data Index: 1158575 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.4806. Min Act: -0.1700

Data Index: 699477 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.4806. Min Act: -0.1700

Data Index: 1067615 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.4181. Min Act: -0.1700

Data Index: 353187 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.3556. Min Act: -0.1700

Data Index: 1162372 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.4181. Min Act: -0.1700

Data Index: 641956 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.3243. Min Act: -0.1700

Data Index: 714339 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.3868. Min Act: -0.1700

Data Index: 404399 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.3556. Min Act: -0.1700

Data Index: 1170371 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.3243. Min Act: -0.1700

Data Index: 162639 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.3868. Min Act: -0.1700

Data Index: 801875 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.3556. Min Act: -0.1700

Data Index: 858324 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 5.8868. Min Range: -5.8868

Max Act: 5.3243. Min Act: -0.1700

Data Index: 492442 (C4 (Web Text))

Max Activating Token Index: 322