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

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

Neuron 40 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: 3.4493. Min Range: -3.4493

Max Act: 3.4493. Min Act: -0.1700

Data Index: 278167 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3865. Min Act: -0.1700

Data Index: 423607 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3865. Min Act: -0.1700

Data Index: 718960 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3708. Min Act: -0.1700

Data Index: 264642 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3865. Min Act: -0.1700

Data Index: 333324 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3080. Min Act: -0.1700

Data Index: 616492 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3080. Min Act: -0.1700

Data Index: 1246423 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.3237. Min Act: -0.1700

Data Index: 462762 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2766. Min Act: -0.1700

Data Index: 463377 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2609. Min Act: -0.1700

Data Index: 487598 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2609. Min Act: -0.1700

Data Index: 1054288 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2923. Min Act: -0.1700

Data Index: 1107585 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2766. Min Act: -0.1700

Data Index: 617985 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2609. Min Act: -0.1700

Data Index: 650926 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2609. Min Act: -0.1700

Data Index: 934395 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2452. Min Act: -0.1700

Data Index: 454106 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2766. Min Act: -0.1700

Data Index: 254368 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2452. Min Act: -0.1700

Data Index: 412190 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2766. Min Act: -0.1700

Data Index: 238438 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 3.4493. Min Range: -3.4493

Max Act: 3.2452. Min Act: -0.1700

Data Index: 841660 (C4 (Web Text))

Max Activating Token Index: 896