Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1962 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.7354. Min Act: -0.1700

Data Index: 1373827 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.6642. Min Act: -0.1700

Data Index: 1555242 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.6210. Min Act: -0.1700

Data Index: 1643617 (Python Code)

Max Activating Token Index: 625

Text #3

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.6023. Min Act: -0.1700

Data Index: 243438 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5713. Min Act: -0.1700

Data Index: 1326423 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5581. Min Act: -0.1700

Data Index: 1285737 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5618. Min Act: -0.1700

Data Index: 704129 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5328. Min Act: -0.1700

Data Index: 789141 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5520. Min Act: -0.1700

Data Index: 1632537 (Python Code)

Max Activating Token Index: 143

Text #9

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5373. Min Act: -0.1700

Data Index: 705262 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5242. Min Act: -0.1700

Data Index: 476055 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5306. Min Act: -0.1700

Data Index: 1611960 (Python Code)

Max Activating Token Index: 667

Text #12

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5183. Min Act: -0.1700

Data Index: 855978 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5101. Min Act: -0.1700

Data Index: 1301417 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1042425 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4732. Min Act: -0.1700

Data Index: 717539 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4841. Min Act: -0.1700

Data Index: 1279007 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4510. Min Act: -0.1700

Data Index: 472922 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4750. Min Act: -0.1700

Data Index: 878712 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4697. Min Act: -0.1700

Data Index: 184012 (C4 (Web Text))

Max Activating Token Index: 577