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

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

Neuron 828 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.5796. Min Act: -0.1700

Data Index: 713506 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.5013. Min Act: -0.1700

Data Index: 1308620 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.3445. Min Act: -0.1700

Data Index: 1123408 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.3131. Min Act: -0.1700

Data Index: 550386 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.3288. Min Act: -0.1700

Data Index: 192460 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.3445. Min Act: -0.1700

Data Index: 610010 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.3288. Min Act: -0.1700

Data Index: 782647 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2974. Min Act: -0.1700

Data Index: 1110593 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2816. Min Act: -0.1700

Data Index: 126320 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2816. Min Act: -0.1700

Data Index: 753557 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2974. Min Act: -0.1700

Data Index: 975677 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2502. Min Act: -0.1700

Data Index: 1060285 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2502. Min Act: -0.1700

Data Index: 173907 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2659. Min Act: -0.1700

Data Index: 1079681 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2816. Min Act: -0.1700

Data Index: 292299 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.1873. Min Act: -0.1700

Data Index: 714023 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2659. Min Act: -0.1700

Data Index: 129880 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2188. Min Act: -0.1700

Data Index: 1303123 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2345. Min Act: -0.1700

Data Index: 1155384 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 3.5796. Min Range: -3.5796

Max Act: 3.2188. Min Act: -0.1700

Data Index: 348644 (C4 (Web Text))

Max Activating Token Index: 672