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

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

Neuron 947 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.2860. Min Act: -0.1700

Data Index: 712681 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.2548. Min Act: -0.1700

Data Index: 871227 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0985. Min Act: -0.1700

Data Index: 425514 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0985. Min Act: -0.1700

Data Index: 1055179 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0048. Min Act: -0.1700

Data Index: 323170 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0360. Min Act: -0.1700

Data Index: 288360 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0048. Min Act: -0.1700

Data Index: 657696 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0048. Min Act: -0.1700

Data Index: 506856 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9735. Min Act: -0.1700

Data Index: 264913 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0360. Min Act: -0.1700

Data Index: 833476 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9735. Min Act: -0.1700

Data Index: 427040 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9423. Min Act: -0.1700

Data Index: 853810 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9423. Min Act: -0.1700

Data Index: 721515 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0048. Min Act: -0.1700

Data Index: 692124 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9110. Min Act: -0.1700

Data Index: 1331858 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.8798. Min Act: -0.1700

Data Index: 396132 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.8798. Min Act: -0.1700

Data Index: 666740 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9110. Min Act: -0.1700

Data Index: 1115234 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9423. Min Act: -0.1700

Data Index: 1131888 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.9110. Min Act: -0.1700

Data Index: 1122697 (C4 (Web Text))

Max Activating Token Index: 842