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

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

Neuron 2003 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.6682. Min Act: -0.1700

Data Index: 1352880 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.4807. Min Act: -0.1700

Data Index: 1190242 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.4495. Min Act: -0.1700

Data Index: 227523 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.5120. Min Act: -0.1700

Data Index: 585093 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.4495. Min Act: -0.1700

Data Index: 1246762 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.4495. Min Act: -0.1700

Data Index: 1265421 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.3557. Min Act: -0.1700

Data Index: 378267 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.3870. Min Act: -0.1700

Data Index: 332640 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.2307. Min Act: -0.1700

Data Index: 239309 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.3870. Min Act: -0.1700

Data Index: 817491 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.2932. Min Act: -0.1700

Data Index: 918933 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.1682. Min Act: -0.1700

Data Index: 470456 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.2307. Min Act: -0.1700

Data Index: 174088 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.1995. Min Act: -0.1700

Data Index: 337322 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.3557. Min Act: -0.1700

Data Index: 210083 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.1682. Min Act: -0.1700

Data Index: 151698 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.2620. Min Act: -0.1700

Data Index: 30607 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.2307. Min Act: -0.1700

Data Index: 43377 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.1057. Min Act: -0.1700

Data Index: 918177 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 5.6682. Min Range: -5.6682

Max Act: 5.1370. Min Act: -0.1700

Data Index: 1076799 (C4 (Web Text))

Max Activating Token Index: 550