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

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

Neuron 194 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: 3.2515. Min Range: -3.2515

Max Act: 3.2515. Min Act: -0.1700

Data Index: 571038 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.2201. Min Act: -0.1700

Data Index: 959221 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.2043. Min Act: -0.1700

Data Index: 24138 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1886. Min Act: -0.1700

Data Index: 29796 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1729. Min Act: -0.1700

Data Index: 258854 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1886. Min Act: -0.1700

Data Index: 758368 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1729. Min Act: -0.1700

Data Index: 229793 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1571. Min Act: -0.1700

Data Index: 1235126 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1256. Min Act: -0.1700

Data Index: 422479 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1256. Min Act: -0.1700

Data Index: 786184 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1099. Min Act: -0.1700

Data Index: 797787 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0783. Min Act: -0.1700

Data Index: 730601 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1414. Min Act: -0.1700

Data Index: 978024 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0468. Min Act: -0.1700

Data Index: 254134 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1256. Min Act: -0.1700

Data Index: 1337044 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0941. Min Act: -0.1700

Data Index: 208629 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0941. Min Act: -0.1700

Data Index: 345051 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0783. Min Act: -0.1700

Data Index: 175317 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0625. Min Act: -0.1700

Data Index: 1268774 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0468. Min Act: -0.1700

Data Index: 244854 (C4 (Web Text))

Max Activating Token Index: 289