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

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

Neuron 1702 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.5084. Min Act: -0.1700

Data Index: 1268118 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.4459. Min Act: -0.1700

Data Index: 452291 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.4147. Min Act: -0.1700

Data Index: 138183 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.4459. Min Act: -0.1700

Data Index: 129997 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.4147. Min Act: -0.1700

Data Index: 703220 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.4147. Min Act: -0.1700

Data Index: 1356596 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.2897. Min Act: -0.1700

Data Index: 1164481 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.2584. Min Act: -0.1700

Data Index: 513577 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.2584. Min Act: -0.1700

Data Index: 421851 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.2584. Min Act: -0.1700

Data Index: 1329408 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.2272. Min Act: -0.1700

Data Index: 1003832 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.1959. Min Act: -0.1699

Data Index: 571703 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.2272. Min Act: -0.1700

Data Index: 566719 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.1959. Min Act: -0.1700

Data Index: 107283 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.2584. Min Act: -0.1700

Data Index: 21073 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.1647. Min Act: -0.1700

Data Index: 629887 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.1959. Min Act: -0.1700

Data Index: 897177 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.1647. Min Act: -0.1700

Data Index: 1210319 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.1959. Min Act: -0.1700

Data Index: 1165507 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 5.5084. Min Range: -5.5084

Max Act: 5.1647. Min Act: -0.1700

Data Index: 1056450 (C4 (Web Text))

Max Activating Token Index: 54