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

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

Neuron 1196 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: 3.9508. Min Range: -3.9508

Max Act: 3.8882. Min Act: -0.1700

Data Index: 450685 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.9195. Min Act: -0.1700

Data Index: 1317745 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.9195. Min Act: -0.1700

Data Index: 120534 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8882. Min Act: -0.1700

Data Index: 521009 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8882. Min Act: -0.1700

Data Index: 98889 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.9508. Min Act: -0.1700

Data Index: 589791 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8726. Min Act: -0.1700

Data Index: 368542 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8726. Min Act: -0.1700

Data Index: 2007 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.9195. Min Act: -0.1700

Data Index: 382077 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.9508. Min Act: -0.1700

Data Index: 885718 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.9195. Min Act: -0.1700

Data Index: 1051898 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.9508. Min Act: -0.1700

Data Index: 493895 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8882. Min Act: -0.1700

Data Index: 777964 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8726. Min Act: -0.1700

Data Index: 874860 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8570. Min Act: -0.1700

Data Index: 738753 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8726. Min Act: -0.1700

Data Index: 101545 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8882. Min Act: -0.1700

Data Index: 327955 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8882. Min Act: -0.1700

Data Index: 498797 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8882. Min Act: -0.1700

Data Index: 1268855 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 3.9508. Min Range: -3.9508

Max Act: 3.8882. Min Act: -0.1700

Data Index: 753322 (C4 (Web Text))

Max Activating Token Index: 579