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

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

Neuron 1516 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.7455. Min Act: -0.1700

Data Index: 1223617 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6829. Min Act: -0.1700

Data Index: 560354 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5890. Min Act: -0.1700

Data Index: 833163 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5733. Min Act: -0.1700

Data Index: 1252157 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5420. Min Act: -0.1700

Data Index: 987282 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5577. Min Act: -0.1700

Data Index: 1313522 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5577. Min Act: -0.1700

Data Index: 124177 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5420. Min Act: -0.1700

Data Index: 544568 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5420. Min Act: -0.1700

Data Index: 1340150 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5420. Min Act: -0.1700

Data Index: 562073 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5420. Min Act: -0.1700

Data Index: 1006674 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4950. Min Act: -0.1700

Data Index: 353129 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4950. Min Act: -0.1700

Data Index: 933137 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4793. Min Act: -0.1700

Data Index: 1298042 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4323. Min Act: -0.1700

Data Index: 775737 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4637. Min Act: -0.1700

Data Index: 1343661 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4637. Min Act: -0.1700

Data Index: 433126 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4637. Min Act: -0.1700

Data Index: 1083975 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4950. Min Act: -0.1700

Data Index: 1311010 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4793. Min Act: -0.1700

Data Index: 39490 (C4 (Web Text))

Max Activating Token Index: 542