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

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

Neuron 1424 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: 5.1640. Min Range: -5.1640

Max Act: 5.1640. Min Act: -0.1700

Data Index: 259941 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 5.1640. Min Range: -5.1640

Max Act: 5.0703. Min Act: -0.1700

Data Index: 876388 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 5.1640. Min Range: -5.1640

Max Act: 5.0390. Min Act: -0.1700

Data Index: 767673 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 5.1640. Min Range: -5.1640

Max Act: 5.0390. Min Act: -0.1700

Data Index: 793828 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 5.1640. Min Range: -5.1640

Max Act: 5.0078. Min Act: -0.1700

Data Index: 1174867 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 5.1640. Min Range: -5.1640

Max Act: 5.0390. Min Act: -0.1700

Data Index: 347951 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 5.1640. Min Range: -5.1640

Max Act: 5.0078. Min Act: -0.1700

Data Index: 765156 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9765. Min Act: -0.1700

Data Index: 121926 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9765. Min Act: -0.1700

Data Index: 247261 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9765. Min Act: -0.1700

Data Index: 185528 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9765. Min Act: -0.1700

Data Index: 231367 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9453. Min Act: -0.1700

Data Index: 654275 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9140. Min Act: -0.1700

Data Index: 912004 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9140. Min Act: -0.1700

Data Index: 779005 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9453. Min Act: -0.1700

Data Index: 819920 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9140. Min Act: -0.1700

Data Index: 838003 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9453. Min Act: -0.1700

Data Index: 888923 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.9140. Min Act: -0.1699

Data Index: 1314710 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.8203. Min Act: -0.1700

Data Index: 145141 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 5.1640. Min Range: -5.1640

Max Act: 4.8828. Min Act: -0.1700

Data Index: 51711 (C4 (Web Text))

Max Activating Token Index: 137