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

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

Neuron 451 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.1810. Min Act: -0.1700

Data Index: 1209288 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.1653. Min Act: -0.1700

Data Index: 1238790 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.1338. Min Act: -0.1700

Data Index: 1213230 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.1338. Min Act: -0.1700

Data Index: 1216478 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.1338. Min Act: -0.1700

Data Index: 268210 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.1023. Min Act: -0.1700

Data Index: 1346267 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.0865. Min Act: -0.1700

Data Index: 1267136 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.0234. Min Act: -0.1700

Data Index: 688098 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.0234. Min Act: -0.1700

Data Index: 364178 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.9918. Min Act: -0.1700

Data Index: 937263 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 3.1810. Min Range: -3.1810

Max Act: 3.0076. Min Act: -0.1700

Data Index: 697758 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.9601. Min Act: -0.1700

Data Index: 124042 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.9601. Min Act: -0.1700

Data Index: 118241 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.9443. Min Act: -0.1700

Data Index: 354937 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.9126. Min Act: -0.1700

Data Index: 864183 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.9126. Min Act: -0.1700

Data Index: 1243905 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.9126. Min Act: -0.1700

Data Index: 519519 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.8967. Min Act: -0.1700

Data Index: 1076561 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.8809. Min Act: -0.1700

Data Index: 821998 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 3.1810. Min Range: -3.1810

Max Act: 2.8967. Min Act: -0.1700

Data Index: 621742 (C4 (Web Text))

Max Activating Token Index: 612