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

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

Neuron 1076 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: 5.3248. Min Range: -5.3248

Max Act: 5.3248. Min Act: -0.1700

Data Index: 243368 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 5.3248. Min Range: -5.3248

Max Act: 5.2623. Min Act: -0.1700

Data Index: 457878 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 5.3248. Min Range: -5.3248

Max Act: 5.1998. Min Act: -0.1700

Data Index: 809516 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 5.3248. Min Range: -5.3248

Max Act: 5.0748. Min Act: -0.1700

Data Index: 17698 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 5.3248. Min Range: -5.3248

Max Act: 5.0748. Min Act: -0.1696

Data Index: 286 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 5.3248. Min Range: -5.3248

Max Act: 5.0123. Min Act: -0.1700

Data Index: 743868 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 5.3248. Min Range: -5.3248

Max Act: 5.0748. Min Act: -0.1700

Data Index: 527175 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 5.3248. Min Range: -5.3248

Max Act: 5.0435. Min Act: -0.1649

Data Index: 1083693 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 5.3248. Min Range: -5.3248

Max Act: 5.0123. Min Act: -0.1699

Data Index: 162942 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 5.3248. Min Range: -5.3248

Max Act: 5.0748. Min Act: -0.1700

Data Index: 768424 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.9810. Min Act: -0.1700

Data Index: 1349599 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.9498. Min Act: -0.1700

Data Index: 815408 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.9498. Min Act: -0.1700

Data Index: 102393 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.9498. Min Act: -0.1700

Data Index: 258909 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.9498. Min Act: -0.1698

Data Index: 1334511 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.9185. Min Act: -0.1699

Data Index: 1247284 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.8873. Min Act: -0.1700

Data Index: 1229967 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.8873. Min Act: -0.1700

Data Index: 913438 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.8560. Min Act: -0.1700

Data Index: 594662 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 5.3248. Min Range: -5.3248

Max Act: 4.8873. Min Act: -0.1700

Data Index: 877020 (C4 (Web Text))

Max Activating Token Index: 608