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

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

Neuron 544 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: 2.9451. Min Range: -2.9451

Max Act: 2.9451. Min Act: -0.1659

Data Index: 86173 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.9370. Min Act: -0.1700

Data Index: 1464662 (Python Code)

Max Activating Token Index: 205

Text #2

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.9111. Min Act: -0.1700

Data Index: 815425 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8985. Min Act: -0.1620

Data Index: 1198632 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8450. Min Act: -0.1699

Data Index: 539392 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8497. Min Act: -0.1700

Data Index: 1441978 (Python Code)

Max Activating Token Index: 384

Text #6

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8362. Min Act: -0.1457

Data Index: 1022933 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8412. Min Act: -0.1699

Data Index: 627801 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8257. Min Act: -0.1700

Data Index: 691903 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8400. Min Act: -0.1700

Data Index: 465475 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7929. Min Act: -0.1699

Data Index: 1312275 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7852. Min Act: -0.1691

Data Index: 1631916 (Python Code)

Max Activating Token Index: 850

Text #12

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7942. Min Act: -0.1700

Data Index: 1643586 (Python Code)

Max Activating Token Index: 551

Text #13

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7999. Min Act: -0.1699

Data Index: 324913 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7876. Min Act: -0.1700

Data Index: 1155103 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7871. Min Act: -0.1700

Data Index: 236067 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7918. Min Act: -0.1573

Data Index: 53922 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8002. Min Act: -0.1700

Data Index: 658727 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7606. Min Act: -0.1700

Data Index: 947125 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7537. Min Act: -0.1176

Data Index: 1566348 (Python Code)

Max Activating Token Index: 952