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

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

Neuron 1764 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.1749. Min Act: -0.1700

Data Index: 751478 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.1119. Min Act: -0.1700

Data Index: 952921 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0804. Min Act: -0.1700

Data Index: 1273655 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0014. Min Act: -0.1700

Data Index: 800023 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0014. Min Act: -0.1700

Data Index: 315095 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9856. Min Act: -0.1700

Data Index: 799469 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9856. Min Act: -0.1700

Data Index: 1313071 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9856. Min Act: -0.1700

Data Index: 286206 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9381. Min Act: -0.1700

Data Index: 1219174 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9223. Min Act: -0.1700

Data Index: 3338 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9223. Min Act: -0.1700

Data Index: 802495 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8906. Min Act: -0.1700

Data Index: 656010 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9064. Min Act: -0.1700

Data Index: 793066 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9064. Min Act: -0.1700

Data Index: 747488 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9064. Min Act: -0.1700

Data Index: 486720 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8906. Min Act: -0.1700

Data Index: 434892 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8906. Min Act: -0.1700

Data Index: 1286527 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8906. Min Act: -0.1700

Data Index: 197953 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8588. Min Act: -0.1700

Data Index: 703123 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8747. Min Act: -0.1700

Data Index: 823756 (C4 (Web Text))

Max Activating Token Index: 118