Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1815 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.8279. Min Act: -0.1698

Data Index: 851387 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.6558. Min Act: -0.1700

Data Index: 1024192 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5932. Min Act: -0.1700

Data Index: 180641 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5775. Min Act: -0.1699

Data Index: 174569 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5775. Min Act: -0.1700

Data Index: 725106 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5775. Min Act: -0.1700

Data Index: 1194491 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5619. Min Act: -0.1700

Data Index: 1168465 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5462. Min Act: -0.1700

Data Index: 1052596 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5619. Min Act: -0.1700

Data Index: 820216 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5462. Min Act: -0.1693

Data Index: 818684 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5462. Min Act: -0.1700

Data Index: 849661 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5305. Min Act: -0.1700

Data Index: 1140402 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5149. Min Act: -0.1700

Data Index: 445030 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.4835. Min Act: -0.1700

Data Index: 1098052 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.4835. Min Act: -0.1700

Data Index: 817387 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.4992. Min Act: -0.1673

Data Index: 517848 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.4835. Min Act: -0.1700

Data Index: 1048131 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.5149. Min Act: -0.1700

Data Index: 1017927 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.4679. Min Act: -0.1700

Data Index: 599329 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 3.8279. Min Range: -3.8279

Max Act: 3.4835. Min Act: -0.1700

Data Index: 81274 (C4 (Web Text))

Max Activating Token Index: 482