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

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

Neuron 915 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.2648. Min Act: -0.1700

Data Index: 669752 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1711. Min Act: -0.1700

Data Index: 141317 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.0148. Min Act: -0.1700

Data Index: 1040824 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.9523. Min Act: -0.1700

Data Index: 854335 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.8898. Min Act: -0.1700

Data Index: 1592059 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.9211. Min Act: -0.1700

Data Index: 1191995 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.7961. Min Act: -0.1700

Data Index: 1004772 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.8586. Min Act: -0.1700

Data Index: 828388 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.8586. Min Act: -0.1700

Data Index: 776462 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.8586. Min Act: -0.1699

Data Index: 917805 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.8898. Min Act: -0.1700

Data Index: 143833 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.8586. Min Act: -0.1700

Data Index: 1445259 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.7961. Min Act: -0.1673

Data Index: 1431443 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.8586. Min Act: -0.1700

Data Index: 532079 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.8273. Min Act: -0.1700

Data Index: 883577 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.7961. Min Act: -0.1700

Data Index: 798250 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.7648. Min Act: -0.1700

Data Index: 604183 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.7648. Min Act: -0.1700

Data Index: 759110 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.7648. Min Act: -0.1700

Data Index: 1083312 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 5.2648. Min Range: -5.2648

Max Act: 4.8273. Min Act: -0.1676

Data Index: 950889 (C4 (Web Text))

Max Activating Token Index: 483