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

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

Neuron 1389 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3652. Min Range: -5.3652

Max Act: 5.3652. Min Act: -0.1700

Data Index: 926477 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 5.3652. Min Range: -5.3652

Max Act: 5.2089. Min Act: -0.1700

Data Index: 803046 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 5.3652. Min Range: -5.3652

Max Act: 5.1464. Min Act: -0.1700

Data Index: 1299374 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 5.3652. Min Range: -5.3652

Max Act: 5.1464. Min Act: -0.1700

Data Index: 1347480 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 5.3652. Min Range: -5.3652

Max Act: 5.1464. Min Act: -0.1700

Data Index: 94705 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 5.3652. Min Range: -5.3652

Max Act: 5.1152. Min Act: -0.1700

Data Index: 763143 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 5.3652. Min Range: -5.3652

Max Act: 5.0839. Min Act: -0.1700

Data Index: 43832 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.9902. Min Act: -0.1700

Data Index: 1271589 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.9902. Min Act: -0.1700

Data Index: 491804 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.9589. Min Act: -0.1700

Data Index: 118561 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.9902. Min Act: -0.1700

Data Index: 1063708 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.8964. Min Act: -0.1700

Data Index: 247648 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.9902. Min Act: -0.1700

Data Index: 849222 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.8652. Min Act: -0.1700

Data Index: 1178391 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.8964. Min Act: -0.1700

Data Index: 355907 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.8964. Min Act: -0.1700

Data Index: 121990 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.8339. Min Act: -0.1700

Data Index: 875248 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.8652. Min Act: -0.1700

Data Index: 765345 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.8339. Min Act: -0.1700

Data Index: 1309824 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 5.3652. Min Range: -5.3652

Max Act: 4.8339. Min Act: -0.1700

Data Index: 380841 (C4 (Web Text))

Max Activating Token Index: 822