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

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

Neuron 1239 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: 5.9725. Min Range: -5.9725

Max Act: 5.9725. Min Act: -0.1700

Data Index: 809158 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.6287. Min Act: -0.1700

Data Index: 692402 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.7850. Min Act: -0.1700

Data Index: 37775 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.6912. Min Act: -0.1700

Data Index: 893766 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.5975. Min Act: -0.1700

Data Index: 200437 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.5975. Min Act: -0.1700

Data Index: 1167266 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.5350. Min Act: -0.1700

Data Index: 1066535 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.4725. Min Act: -0.1700

Data Index: 808630 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.4412. Min Act: -0.1700

Data Index: 552423 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.4100. Min Act: -0.1700

Data Index: 1231961 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.4725. Min Act: -0.1700

Data Index: 375255 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.4412. Min Act: -0.1700

Data Index: 609204 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.1287. Min Act: -0.1700

Data Index: 801472 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.3787. Min Act: -0.1700

Data Index: 302392 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.3787. Min Act: -0.1700

Data Index: 789377 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.3475. Min Act: -0.1700

Data Index: 62251 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.3475. Min Act: -0.1700

Data Index: 183630 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.3475. Min Act: -0.1700

Data Index: 906703 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.2850. Min Act: -0.1700

Data Index: 1066125 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 5.9725. Min Range: -5.9725

Max Act: 5.3162. Min Act: -0.1700

Data Index: 1043909 (C4 (Web Text))

Max Activating Token Index: 236