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

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

Neuron 389 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: 3.1967. Min Range: -3.1967

Max Act: 3.1967. Min Act: -0.1700

Data Index: 1466249 (Python Code)

Max Activating Token Index: 983

Text #1

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.1699. Min Act: -0.1700

Data Index: 687967 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.1870. Min Act: -0.1700

Data Index: 467934 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.1336. Min Act: -0.1700

Data Index: 930987 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0889. Min Act: -0.1700

Data Index: 534468 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0716. Min Act: -0.1700

Data Index: 947473 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0573. Min Act: -0.1700

Data Index: 1103910 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0568. Min Act: -0.1700

Data Index: 1896 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0386. Min Act: -0.1700

Data Index: 1021356 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0360. Min Act: -0.1700

Data Index: 855069 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0514. Min Act: -0.1700

Data Index: 815157 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0424. Min Act: -0.1700

Data Index: 381793 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0252. Min Act: -0.1700

Data Index: 800140 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0291. Min Act: -0.1700

Data Index: 1177179 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0327. Min Act: -0.1700

Data Index: 205661 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0020. Min Act: -0.1699

Data Index: 483582 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0225. Min Act: -0.1700

Data Index: 947251 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 3.1967. Min Range: -3.1967

Max Act: 3.0058. Min Act: -0.1700

Data Index: 482803 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.9991. Min Act: -0.1699

Data Index: 1007839 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 3.1967. Min Range: -3.1967

Max Act: 2.9915. Min Act: -0.1700

Data Index: 157342 (C4 (Web Text))

Max Activating Token Index: 747