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

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

Neuron 624 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: 5.8428. Min Range: -5.8428

Max Act: 5.8428. Min Act: -0.1699

Data Index: 882203 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.7490. Min Act: -0.1700

Data Index: 1341459 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.7803. Min Act: -0.1700

Data Index: 992136 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.6865. Min Act: -0.1700

Data Index: 49875 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.6553. Min Act: -0.1700

Data Index: 645215 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5928. Min Act: -0.1700

Data Index: 4574 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.6553. Min Act: -0.1700

Data Index: 847950 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5928. Min Act: -0.1699

Data Index: 1161740 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.6240. Min Act: -0.1700

Data Index: 354329 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5615. Min Act: -0.1700

Data Index: 357008 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5615. Min Act: -0.1700

Data Index: 1121691 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5303. Min Act: -0.1699

Data Index: 406200 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5303. Min Act: -0.1700

Data Index: 334041 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5615. Min Act: -0.1699

Data Index: 628407 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5303. Min Act: -0.1699

Data Index: 773643 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5303. Min Act: -0.1700

Data Index: 1262403 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5303. Min Act: -0.1700

Data Index: 252057 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.4990. Min Act: -0.1700

Data Index: 187988 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.5303. Min Act: -0.1700

Data Index: 302340 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 5.8428. Min Range: -5.8428

Max Act: 5.4990. Min Act: -0.1700

Data Index: 1293781 (C4 (Web Text))

Max Activating Token Index: 91