Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 407 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.3234. Min Range: -4.3234

Max Act: 4.3234. Min Act: -0.1700

Data Index: 774951 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.3234. Min Range: -4.3234

Max Act: 4.1671. Min Act: -0.1700

Data Index: 537816 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.3234. Min Range: -4.3234

Max Act: 4.0733. Min Act: -0.1700

Data Index: 896021 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.3234. Min Range: -4.3234

Max Act: 4.0733. Min Act: -0.1700

Data Index: 7867 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.3234. Min Range: -4.3234

Max Act: 4.0733. Min Act: -0.1700

Data Index: 638724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9795. Min Act: -0.1700

Data Index: 313873 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9482. Min Act: -0.1700

Data Index: 908782 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9795. Min Act: -0.1700

Data Index: 936587 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9795. Min Act: -0.1699

Data Index: 9901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9795. Min Act: -0.1700

Data Index: 1083468 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9170. Min Act: -0.1700

Data Index: 153685 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9170. Min Act: -0.1700

Data Index: 900396 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9170. Min Act: -0.1700

Data Index: 959424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1190781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.8544. Min Act: -0.1700

Data Index: 164186 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9482. Min Act: -0.1700

Data Index: 1039921 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.8544. Min Act: -0.1700

Data Index: 359988 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.8857. Min Act: -0.1700

Data Index: 634916 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.8544. Min Act: -0.1700

Data Index: 1022066 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9170. Min Act: -0.1700

Data Index: 587802 (C4 (Web Text))

Max Activating Token Index: 990