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

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

Neuron 751 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.3656. Min Act: -0.1700

Data Index: 559883 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.2714. Min Act: -0.1700

Data Index: 681704 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.3028. Min Act: -0.1700

Data Index: 904496 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.2557. Min Act: -0.1700

Data Index: 78302 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.2714. Min Act: -0.1700

Data Index: 1164269 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.2871. Min Act: -0.1700

Data Index: 1293976 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.2400. Min Act: -0.1700

Data Index: 672498 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.2243. Min Act: -0.1700

Data Index: 372005 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.2871. Min Act: -0.1700

Data Index: 295469 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.2400. Min Act: -0.1700

Data Index: 121506 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.2243. Min Act: -0.1700

Data Index: 1323763 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.1613. Min Act: -0.1700

Data Index: 1329448 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.1456. Min Act: -0.1700

Data Index: 640469 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.1141. Min Act: -0.1700

Data Index: 57968 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.1141. Min Act: -0.1700

Data Index: 898203 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.1298. Min Act: -0.1700

Data Index: 382182 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.0825. Min Act: -0.1700

Data Index: 691462 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.1141. Min Act: -0.1700

Data Index: 408082 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.0825. Min Act: -0.1700

Data Index: 107274 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 3.3656. Min Range: -3.3656

Max Act: 3.0983. Min Act: -0.1700

Data Index: 620293 (C4 (Web Text))

Max Activating Token Index: 631