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

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

Neuron 1800 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: 5.3071. Min Range: -5.3071

Max Act: 5.3071. Min Act: -0.1700

Data Index: 1070174 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.2758. Min Act: -0.1699

Data Index: 510418 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.2602. Min Act: -0.1700

Data Index: 559089 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.1821. Min Act: -0.1700

Data Index: 709836 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.1352. Min Act: -0.1700

Data Index: 40545 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.1039. Min Act: -0.1700

Data Index: 138690 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.0727. Min Act: -0.1700

Data Index: 269058 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.1196. Min Act: -0.1700

Data Index: 107426 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.0727. Min Act: -0.1700

Data Index: 1233685 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.0883. Min Act: -0.1700

Data Index: 433876 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.1039. Min Act: -0.1700

Data Index: 350683 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 5.3071. Min Range: -5.3071

Max Act: 4.9946. Min Act: -0.1700

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 5.3071. Min Range: -5.3071

Max Act: 4.9946. Min Act: -0.1700

Data Index: 964517 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.0258. Min Act: -0.1700

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.0414. Min Act: -0.1699

Data Index: 1053595 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.0571. Min Act: -0.1700

Data Index: 829220 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.0102. Min Act: -0.1700

Data Index: 773873 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 5.3071. Min Range: -5.3071

Max Act: 5.0571. Min Act: -0.1700

Data Index: 662310 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 5.3071. Min Range: -5.3071

Max Act: 4.9164. Min Act: -0.1700

Data Index: 1085407 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 5.3071. Min Range: -5.3071

Max Act: 4.9321. Min Act: -0.1700

Data Index: 252230 (C4 (Web Text))

Max Activating Token Index: 523