Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1206 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.3222. Min Act: -0.1700

Data Index: 401859 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2751. Min Act: -0.1700

Data Index: 407941 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2908. Min Act: -0.1700

Data Index: 634844 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2437. Min Act: -0.1700

Data Index: 520243 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2279. Min Act: -0.1700

Data Index: 61946 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2751. Min Act: -0.1700

Data Index: 246697 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2594. Min Act: -0.1700

Data Index: 424132 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2437. Min Act: -0.1700

Data Index: 853503 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2279. Min Act: -0.1700

Data Index: 762194 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2279. Min Act: -0.1700

Data Index: 393087 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2279. Min Act: -0.1700

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2122. Min Act: -0.1700

Data Index: 809645 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2594. Min Act: -0.1700

Data Index: 1252974 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2279. Min Act: -0.1700

Data Index: 56820 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2437. Min Act: -0.1700

Data Index: 986339 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2122. Min Act: -0.1700

Data Index: 1083298 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2122. Min Act: -0.1700

Data Index: 772045 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.1965. Min Act: -0.1700

Data Index: 1169656 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2122. Min Act: -0.1700

Data Index: 852612 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 3.3222. Min Range: -3.3222

Max Act: 3.2122. Min Act: -0.1700

Data Index: 494872 (C4 (Web Text))

Max Activating Token Index: 480