Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1257 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.4686. Min Act: -0.1692

Data Index: 147084 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.4059. Min Act: -0.1691

Data Index: 1338581 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.3588. Min Act: -0.1699

Data Index: 1002323 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2960. Min Act: -0.1699

Data Index: 1038438 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2803. Min Act: -0.1698

Data Index: 140405 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2489. Min Act: -0.1700

Data Index: 59029 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2646. Min Act: -0.1697

Data Index: 620779 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2489. Min Act: -0.1699

Data Index: 282540 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2646. Min Act: -0.1699

Data Index: 658472 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2646. Min Act: -0.1682

Data Index: 307520 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2489. Min Act: -0.1699

Data Index: 773770 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2332. Min Act: -0.1698

Data Index: 153018 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2174. Min Act: -0.1700

Data Index: 210840 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2174. Min Act: -0.1696

Data Index: 498129 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2174. Min Act: -0.1700

Data Index: 615677 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2174. Min Act: -0.1699

Data Index: 606254 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2017. Min Act: -0.1686

Data Index: 922870 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2174. Min Act: -0.1699

Data Index: 714812 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2017. Min Act: -0.1692

Data Index: 278217 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 3.4686. Min Range: -3.4686

Max Act: 3.2017. Min Act: -0.1686

Data Index: 1055690 (C4 (Web Text))

Max Activating Token Index: 766