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

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

Neuron 413 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: 5.0295. Min Range: -5.0295

Max Act: 5.0295. Min Act: -0.1699

Data Index: 1413236 (Python Code)

Max Activating Token Index: 724

Text #1

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.8420. Min Act: -0.1700

Data Index: 1571402 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.7795. Min Act: -0.1700

Data Index: 582147 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.7795. Min Act: -0.1529

Data Index: 1471991 (Python Code)

Max Activating Token Index: 442

Text #4

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.7482. Min Act: -0.1669

Data Index: 1401745 (Python Code)

Max Activating Token Index: 263

Text #5

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.7482. Min Act: -0.1668

Data Index: 1409483 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.7170. Min Act: -0.1700

Data Index: 1473148 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.6857. Min Act: -0.1700

Data Index: 1596321 (Python Code)

Max Activating Token Index: 227

Text #8

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.6545. Min Act: -0.1700

Data Index: 1568508 (Python Code)

Max Activating Token Index: 871

Text #9

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.6232. Min Act: -0.1699

Data Index: 1436657 (Python Code)

Max Activating Token Index: 809

Text #10

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.6232. Min Act: -0.1700

Data Index: 1584359 (Python Code)

Max Activating Token Index: 229

Text #11

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.6232. Min Act: -0.1697

Data Index: 1622239 (Python Code)

Max Activating Token Index: 907

Text #12

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.6232. Min Act: -0.1699

Data Index: 1501671 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.6232. Min Act: -0.1700

Data Index: 1533670 (Python Code)

Max Activating Token Index: 749

Text #14

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.5920. Min Act: -0.1700

Data Index: 1481402 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.5920. Min Act: -0.1699

Data Index: 1536930 (Python Code)

Max Activating Token Index: 497

Text #16

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.6232. Min Act: -0.1699

Data Index: 1508286 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.5607. Min Act: -0.1700

Data Index: 1559558 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.5607. Min Act: -0.1700

Data Index: 1415411 (Python Code)

Max Activating Token Index: 436

Text #19

Max Range: 5.0295. Min Range: -5.0295

Max Act: 4.5607. Min Act: -0.1699

Data Index: 1597291 (Python Code)

Max Activating Token Index: 574