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

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

Neuron 1806 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: 5.6332. Min Range: -5.6332

Max Act: 5.6332. Min Act: -0.1700

Data Index: 234612 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.6020. Min Act: -0.1700

Data Index: 1438 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.6020. Min Act: -0.1700

Data Index: 804505 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.6020. Min Act: -0.1700

Data Index: 1045614 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.5238. Min Act: -0.1700

Data Index: 1073797 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.6020. Min Act: -0.1700

Data Index: 72209 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.4926. Min Act: -0.1700

Data Index: 284688 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.4301. Min Act: -0.1700

Data Index: 748077 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.3988. Min Act: -0.1700

Data Index: 13219 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.3676. Min Act: -0.1700

Data Index: 1240609 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.4613. Min Act: -0.1700

Data Index: 538932 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.3988. Min Act: -0.1700

Data Index: 1138352 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.4145. Min Act: -0.1700

Data Index: 776880 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.3676. Min Act: -0.1700

Data Index: 1228981 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.3520. Min Act: -0.1700

Data Index: 1046903 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.3363. Min Act: -0.1700

Data Index: 1028667 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.3832. Min Act: -0.1700

Data Index: 848412 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.3363. Min Act: -0.1700

Data Index: 1009958 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.2738. Min Act: -0.1700

Data Index: 1150164 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 5.6332. Min Range: -5.6332

Max Act: 5.3520. Min Act: -0.1700

Data Index: 68656 (C4 (Web Text))

Max Activating Token Index: 586