Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 983 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.4808. Min Act: -0.1700

Data Index: 92363 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.2308. Min Act: -0.1700

Data Index: 548125 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.2621. Min Act: -0.1673

Data Index: 657516 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.2621. Min Act: -0.1700

Data Index: 165247 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.2308. Min Act: -0.1691

Data Index: 1350232 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.2621. Min Act: -0.1700

Data Index: 418502 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.2621. Min Act: -0.1700

Data Index: 304545 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.2308. Min Act: -0.1700

Data Index: 1226413 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.2308. Min Act: -0.1700

Data Index: 1127949 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1996. Min Act: -0.1700

Data Index: 765645 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1683. Min Act: -0.1700

Data Index: 749460 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1996. Min Act: -0.1700

Data Index: 782781 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1683. Min Act: -0.1700

Data Index: 563603 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1371. Min Act: -0.1700

Data Index: 1164985 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1683. Min Act: -0.1700

Data Index: 110169 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1371. Min Act: -0.1700

Data Index: 176254 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1683. Min Act: -0.1700

Data Index: 1232524 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1058. Min Act: -0.1700

Data Index: 1010614 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1371. Min Act: -0.1700

Data Index: 381004 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 5.4808. Min Range: -5.4808

Max Act: 5.1058. Min Act: -0.1700

Data Index: 473976 (C4 (Web Text))

Max Activating Token Index: 184