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

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

Neuron 1545 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7816. Min Act: -0.1700

Data Index: 221545 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7816. Min Act: -0.1700

Data Index: 771749 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7034. Min Act: -0.1700

Data Index: 764177 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6564. Min Act: -0.1700

Data Index: 1187040 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6721. Min Act: -0.1700

Data Index: 1278147 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6408. Min Act: -0.1700

Data Index: 415644 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6408. Min Act: -0.1700

Data Index: 1013613 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5782. Min Act: -0.1700

Data Index: 1060463 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5782. Min Act: -0.1700

Data Index: 796885 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5782. Min Act: -0.1700

Data Index: 918416 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5625. Min Act: -0.1700

Data Index: 816028 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5469. Min Act: -0.1700

Data Index: 809877 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5469. Min Act: -0.1700

Data Index: 837032 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5155. Min Act: -0.1700

Data Index: 312784 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5155. Min Act: -0.1700

Data Index: 344277 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5312. Min Act: -0.1700

Data Index: 472565 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5312. Min Act: -0.1700

Data Index: 60175 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.4999. Min Act: -0.1700

Data Index: 788422 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.4999. Min Act: -0.1700

Data Index: 1187363 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.5155. Min Act: -0.1700

Data Index: 150476 (C4 (Web Text))

Max Activating Token Index: 979