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

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

Neuron 108 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: 5.3842. Min Range: -5.3842

Max Act: 5.3842. Min Act: -0.1700

Data Index: 1044947 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.2905. Min Act: -0.1700

Data Index: 945522 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.3530. Min Act: -0.1700

Data Index: 290079 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.2905. Min Act: -0.1700

Data Index: 209995 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.3217. Min Act: -0.1700

Data Index: 1133210 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.3217. Min Act: -0.1700

Data Index: 234747 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.2592. Min Act: -0.1700

Data Index: 1186393 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1967. Min Act: -0.1700

Data Index: 520807 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1967. Min Act: -0.1700

Data Index: 494732 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1967. Min Act: -0.1700

Data Index: 51952 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1967. Min Act: -0.1700

Data Index: 1218741 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1655. Min Act: -0.1700

Data Index: 628460 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1967. Min Act: -0.1700

Data Index: 1090334 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1342. Min Act: -0.1700

Data Index: 93346 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1342. Min Act: -0.1700

Data Index: 597353 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1342. Min Act: -0.1700

Data Index: 62884 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1030. Min Act: -0.1700

Data Index: 383081 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1342. Min Act: -0.1700

Data Index: 513836 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1065837 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 5.3842. Min Range: -5.3842

Max Act: 5.0717. Min Act: -0.1700

Data Index: 96195 (C4 (Web Text))

Max Activating Token Index: 368