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

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

Neuron 412 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.9578. Min Act: -0.1699

Data Index: 978610 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.7390. Min Act: -0.1700

Data Index: 962814 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.7390. Min Act: -0.1700

Data Index: 1325404 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.7078. Min Act: -0.1700

Data Index: 601983 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.6765. Min Act: -0.1700

Data Index: 1234295 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.6453. Min Act: -0.1700

Data Index: 8764 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.6453. Min Act: -0.1700

Data Index: 139995 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.6140. Min Act: -0.1700

Data Index: 518520 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.6140. Min Act: -0.1699

Data Index: 778859 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.5515. Min Act: -0.1700

Data Index: 567298 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.6140. Min Act: -0.1699

Data Index: 1350934 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.6140. Min Act: -0.1700

Data Index: 227738 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.5203. Min Act: -0.1700

Data Index: 719273 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.5203. Min Act: -0.1700

Data Index: 1084899 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.5515. Min Act: -0.1700

Data Index: 490197 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.5828. Min Act: -0.1699

Data Index: 673252 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.5203. Min Act: -0.1699

Data Index: 365260 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.5203. Min Act: -0.1700

Data Index: 369706 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.5203. Min Act: -0.1700

Data Index: 1100567 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 4.9578. Min Range: -4.9578

Max Act: 4.5828. Min Act: -0.1699

Data Index: 55227 (C4 (Web Text))

Max Activating Token Index: 541