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

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

Neuron 2019 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: 3.0833. Min Range: -3.0833

Max Act: 3.0833. Min Act: -0.1700

Data Index: 374628 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0833. Min Act: -0.1700

Data Index: 305215 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0833. Min Act: -0.1700

Data Index: 1237315 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 297297 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 260027 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 976924 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0518. Min Act: -0.1700

Data Index: 480805 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0518. Min Act: -0.1700

Data Index: 695299 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 1042664 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 747131 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 1228426 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 151179 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 1257377 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 190835 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 900083 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 306241 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 990735 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0360. Min Act: -0.1700

Data Index: 17254 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0202. Min Act: -0.1700

Data Index: 199167 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 3.0833. Min Range: -3.0833

Max Act: 3.0202. Min Act: -0.1700

Data Index: 411878 (C4 (Web Text))

Max Activating Token Index: 816