Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1032 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.1205. Min Act: -0.1700

Data Index: 252039 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.1363. Min Act: -0.1700

Data Index: 303739 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0890. Min Act: -0.1700

Data Index: 93821 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0417. Min Act: -0.1700

Data Index: 1117649 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0574. Min Act: -0.1700

Data Index: 874239 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0101. Min Act: -0.1700

Data Index: 794083 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0259. Min Act: -0.1700

Data Index: 1286121 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0259. Min Act: -0.1700

Data Index: 567758 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9942. Min Act: -0.1700

Data Index: 44305 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9942. Min Act: -0.1700

Data Index: 294510 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9942. Min Act: -0.1700

Data Index: 457752 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9942. Min Act: -0.1700

Data Index: 1334280 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0259. Min Act: -0.1700

Data Index: 241774 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9784. Min Act: -0.1700

Data Index: 1053859 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9468. Min Act: -0.1700

Data Index: 872310 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9784. Min Act: -0.1700

Data Index: 154281 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9784. Min Act: -0.1700

Data Index: 306320 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9784. Min Act: -0.1700

Data Index: 1165176 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0259. Min Act: -0.1700

Data Index: 1358890 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9784. Min Act: -0.1700

Data Index: 755500 (C4 (Web Text))

Max Activating Token Index: 182