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

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

Neuron 95 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: 3.8008. Min Range: -3.8008

Max Act: 3.8008. Min Act: -0.1689

Data Index: 244264 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.7915. Min Act: -0.1699

Data Index: 1655122 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.7151. Min Act: -0.1665

Data Index: 51896 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.7373. Min Act: -0.1700

Data Index: 1399028 (Python Code)

Max Activating Token Index: 859

Text #4

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.7151. Min Act: -0.1693

Data Index: 1506016 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.7138. Min Act: 0.0679

Data Index: 1618178 (Python Code)

Max Activating Token Index: 570

Text #6

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.6561. Min Act: -0.1692

Data Index: 1231328 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.6727. Min Act: -0.1401

Data Index: 1178115 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.6597. Min Act: -0.1700

Data Index: 1373700 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.5502. Min Act: -0.1700

Data Index: 750770 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.5634. Min Act: -0.1699

Data Index: 1574022 (Python Code)

Max Activating Token Index: 418

Text #11

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.5392. Min Act: -0.1665

Data Index: 1317815 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.5207. Min Act: -0.1699

Data Index: 1463923 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.5178. Min Act: -0.1079

Data Index: 1648349 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.4946. Min Act: -0.1699

Data Index: 1406588 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.4610. Min Act: -0.1699

Data Index: 1424336 (Python Code)

Max Activating Token Index: 606

Text #16

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.4865. Min Act: -0.1700

Data Index: 1479379 (Python Code)

Max Activating Token Index: 933

Text #17

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.4765. Min Act: -0.1699

Data Index: 810293 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.4803. Min Act: -0.1700

Data Index: 870098 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 3.8008. Min Range: -3.8008

Max Act: 3.4769. Min Act: -0.1699

Data Index: 782818 (C4 (Web Text))

Max Activating Token Index: 869