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

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

Neuron 1109 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: 4.8015. Min Range: -4.8015

Max Act: 4.8015. Min Act: -0.1700

Data Index: 1634665 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.7684. Min Act: -0.1700

Data Index: 940676 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.6084. Min Act: -0.1700

Data Index: 1575731 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.6125. Min Act: -0.1700

Data Index: 1471831 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.5827. Min Act: -0.1700

Data Index: 316721 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.5633. Min Act: -0.1700

Data Index: 1655759 (Python Code)

Max Activating Token Index: 491

Text #6

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.5208. Min Act: -0.1700

Data Index: 1105040 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.4675. Min Act: -0.1700

Data Index: 1424245 (Python Code)

Max Activating Token Index: 756

Text #8

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.4347. Min Act: -0.1700

Data Index: 1495765 (Python Code)

Max Activating Token Index: 319

Text #9

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.4594. Min Act: -0.1700

Data Index: 1409790 (Python Code)

Max Activating Token Index: 423

Text #10

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.4236. Min Act: -0.1700

Data Index: 968689 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.3567. Min Act: -0.1700

Data Index: 942562 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.2807. Min Act: -0.1700

Data Index: 1332050 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.2524. Min Act: -0.1700

Data Index: 1326701 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.1667. Min Act: -0.1700

Data Index: 824865 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.1257. Min Act: -0.1700

Data Index: 1442045 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 4.8015. Min Range: -4.8015

Max Act: 3.9883. Min Act: -0.1700

Data Index: 537581 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 4.8015. Min Range: -4.8015

Max Act: 3.9823. Min Act: -0.1700

Data Index: 1162159 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 4.8015. Min Range: -4.8015

Max Act: 4.0645. Min Act: -0.1700

Data Index: 353373 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 4.8015. Min Range: -4.8015

Max Act: 3.9029. Min Act: -0.1700

Data Index: 566295 (C4 (Web Text))

Max Activating Token Index: 973