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

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

Neuron 743 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.3471. Min Range: -11.3471

Max Act: 11.3471. Min Act: -0.1700

Data Index: 715999 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.7846. Min Act: -0.1700

Data Index: 666510 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.7846. Min Act: -0.1700

Data Index: 1340465 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.7221. Min Act: -0.1700

Data Index: 584427 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.5346. Min Act: -0.1700

Data Index: 1174662 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.5971. Min Act: -0.1700

Data Index: 48046 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.5346. Min Act: -0.1700

Data Index: 852978 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.5346. Min Act: -0.1700

Data Index: 1190367 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.5971. Min Act: -0.1700

Data Index: 370782 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.5346. Min Act: -0.1700

Data Index: 336583 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.3471. Min Act: -0.1700

Data Index: 894643 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.4721. Min Act: -0.1700

Data Index: 284230 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.4096. Min Act: -0.1700

Data Index: 1312727 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.3471. Min Act: -0.1700

Data Index: 530180 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.2846. Min Act: -0.1700

Data Index: 531985 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.3471. Min Act: -0.1700

Data Index: 1079236 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.2846. Min Act: -0.1700

Data Index: 788083 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.2846. Min Act: -0.1700

Data Index: 657073 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.1596. Min Act: -0.1700

Data Index: 223692 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 11.3471. Min Range: -11.3471

Max Act: 10.0971. Min Act: -0.1699

Data Index: 1033011 (C4 (Web Text))

Max Activating Token Index: 51