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

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

Neuron 1727 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.5856. Min Act: -0.1700

Data Index: 1181974 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.4606. Min Act: -0.1700

Data Index: 988208 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.5231. Min Act: -0.1700

Data Index: 192860 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.4293. Min Act: -0.1700

Data Index: 566670 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.4606. Min Act: -0.1700

Data Index: 90036 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.4293. Min Act: -0.1700

Data Index: 589438 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.3668. Min Act: -0.1700

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.3981. Min Act: -0.1699

Data Index: 1347051 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.3043. Min Act: -0.1700

Data Index: 921290 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.3668. Min Act: -0.1700

Data Index: 786486 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.3668. Min Act: -0.1700

Data Index: 1356591 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.2731. Min Act: -0.1700

Data Index: 939396 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.3668. Min Act: -0.1700

Data Index: 771929 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.2731. Min Act: -0.1700

Data Index: 423700 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.2731. Min Act: -0.1700

Data Index: 1294340 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.3356. Min Act: -0.1700

Data Index: 666806 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.2731. Min Act: -0.1700

Data Index: 56609 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.2418. Min Act: -0.1700

Data Index: 983672 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.2418. Min Act: -0.1700

Data Index: 453450 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 5.5856. Min Range: -5.5856

Max Act: 5.2731. Min Act: -0.1700

Data Index: 408362 (C4 (Web Text))

Max Activating Token Index: 898