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

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

Neuron 519 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: 5.4514. Min Range: -5.4514

Max Act: 5.4514. Min Act: -0.1700

Data Index: 245326 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.4514. Min Act: -0.1700

Data Index: 1069713 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.4202. Min Act: -0.1700

Data Index: 368357 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.2639. Min Act: -0.1700

Data Index: 390846 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.3264. Min Act: -0.1700

Data Index: 72505 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.1702. Min Act: -0.1700

Data Index: 316251 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.2639. Min Act: -0.1700

Data Index: 1323286 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.1702. Min Act: -0.1700

Data Index: 256883 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.1702. Min Act: -0.1700

Data Index: 1052052 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.2327. Min Act: -0.1700

Data Index: 1086749 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.2327. Min Act: -0.1700

Data Index: 90842 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.2327. Min Act: -0.1700

Data Index: 129931 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.2014. Min Act: -0.1700

Data Index: 1248155 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.2327. Min Act: -0.1700

Data Index: 1239604 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.3264. Min Act: -0.1700

Data Index: 1029861 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.2639. Min Act: -0.1700

Data Index: 786738 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.1389. Min Act: -0.1700

Data Index: 984926 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.2014. Min Act: -0.1700

Data Index: 797674 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.1389. Min Act: -0.1700

Data Index: 977353 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 5.4514. Min Range: -5.4514

Max Act: 5.1389. Min Act: -0.1700

Data Index: 931028 (C4 (Web Text))

Max Activating Token Index: 606