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

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

Neuron 732 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4149. Min Range: -8.4149

Max Act: 8.4149. Min Act: -0.1700

Data Index: 849683 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 8.4149. Min Range: -8.4149

Max Act: 7.1649. Min Act: -0.1699

Data Index: 600132 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 8.4149. Min Range: -8.4149

Max Act: 7.1649. Min Act: -0.1700

Data Index: 701243 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 8.4149. Min Range: -8.4149

Max Act: 7.0712. Min Act: -0.1700

Data Index: 591476 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.5087. Min Act: -0.1698

Data Index: 607383 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.5087. Min Act: -0.1698

Data Index: 1306886 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.5087. Min Act: -0.1699

Data Index: 1302831 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.5399. Min Act: -0.1699

Data Index: 313810 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.4774. Min Act: -0.1698

Data Index: 299639 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.4149. Min Act: -0.1698

Data Index: 7536 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.3837. Min Act: -0.1699

Data Index: 283156 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.3837. Min Act: -0.1700

Data Index: 921448 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.3524. Min Act: -0.1700

Data Index: 379997 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.3524. Min Act: -0.1699

Data Index: 599185 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.3837. Min Act: -0.1699

Data Index: 202218 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.3524. Min Act: -0.1698

Data Index: 616806 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.2899. Min Act: -0.1699

Data Index: 350974 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.3212. Min Act: -0.1698

Data Index: 397120 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.2899. Min Act: -0.1700

Data Index: 644627 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 8.4149. Min Range: -8.4149

Max Act: 6.2587. Min Act: -0.1698

Data Index: 716483 (C4 (Web Text))

Max Activating Token Index: 485