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

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

Neuron 1776 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.3491. Min Act: -0.1700

Data Index: 1114580 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.3491. Min Act: -0.1700

Data Index: 1645778 (Python Code)

Max Activating Token Index: 389

Text #2

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.3020. Min Act: -0.1700

Data Index: 1413989 (Python Code)

Max Activating Token Index: 285

Text #3

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.3020. Min Act: -0.1700

Data Index: 1482945 (Python Code)

Max Activating Token Index: 671

Text #4

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2863. Min Act: -0.1700

Data Index: 1549289 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2392. Min Act: -0.1700

Data Index: 1639604 (Python Code)

Max Activating Token Index: 521

Text #6

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2077. Min Act: -0.1700

Data Index: 594776 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2234. Min Act: -0.1700

Data Index: 1460362 (Python Code)

Max Activating Token Index: 722

Text #8

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1920. Min Act: -0.1700

Data Index: 1435381 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2077. Min Act: -0.1700

Data Index: 1557018 (Python Code)

Max Activating Token Index: 529

Text #10

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2077. Min Act: -0.1700

Data Index: 378114 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2077. Min Act: -0.1700

Data Index: 952493 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2077. Min Act: -0.1700

Data Index: 40735 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1920. Min Act: -0.1700

Data Index: 1017527 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2077. Min Act: -0.1700

Data Index: 841772 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1920. Min Act: -0.1700

Data Index: 92082 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1763. Min Act: -0.1700

Data Index: 1347335 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1763. Min Act: -0.1700

Data Index: 1580017 (Python Code)

Max Activating Token Index: 346

Text #18

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1605. Min Act: -0.1700

Data Index: 1457772 (Python Code)

Max Activating Token Index: 960

Text #19

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1763. Min Act: -0.1699

Data Index: 1624156 (Python Code)

Max Activating Token Index: 599