Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 683 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.7418. Min Act: -0.1700

Data Index: 1573031 (Python Code)

Max Activating Token Index: 314

Text #1

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.6679. Min Act: -0.1692

Data Index: 1529506 (Python Code)

Max Activating Token Index: 153

Text #2

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.6453. Min Act: -0.1700

Data Index: 1522100 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.6652. Min Act: -0.1700

Data Index: 1498009 (Python Code)

Max Activating Token Index: 559

Text #4

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.6558. Min Act: -0.1700

Data Index: 1508107 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.5783. Min Act: -0.1685

Data Index: 1422613 (Python Code)

Max Activating Token Index: 248

Text #6

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.5266. Min Act: -0.1700

Data Index: 1565323 (Python Code)

Max Activating Token Index: 206

Text #7

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.5044. Min Act: -0.1700

Data Index: 1421278 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.5061. Min Act: -0.1700

Data Index: 1390833 (Python Code)

Max Activating Token Index: 620

Text #9

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.4732. Min Act: -0.1700

Data Index: 1389777 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.3685. Min Act: -0.1700

Data Index: 1603363 (Python Code)

Max Activating Token Index: 826

Text #11

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.3301. Min Act: -0.1700

Data Index: 1530158 (Python Code)

Max Activating Token Index: 1015

Text #12

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.2865. Min Act: -0.1700

Data Index: 1651549 (Python Code)

Max Activating Token Index: 509

Text #13

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.2821. Min Act: -0.1700

Data Index: 1507098 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.2889. Min Act: -0.1698

Data Index: 76210 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.2675. Min Act: -0.1695

Data Index: 33003 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.2569. Min Act: -0.1699

Data Index: 1564301 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.2572. Min Act: -0.1646

Data Index: 1404450 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.2474. Min Act: -0.1690

Data Index: 1539616 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 4.7418. Min Range: -4.7418

Max Act: 4.2144. Min Act: -0.1700

Data Index: 1443765 (Python Code)

Max Activating Token Index: 903