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

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

Neuron 1556 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: 4.0652. Min Range: -4.0652

Max Act: 4.0652. Min Act: -0.1700

Data Index: 798897 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 4.0652. Min Range: -4.0652

Max Act: 4.0360. Min Act: -0.1205

Data Index: 357339 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9396. Min Act: -0.1700

Data Index: 492166 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9436. Min Act: -0.1700

Data Index: 600723 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9484. Min Act: -0.1700

Data Index: 263024 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8797. Min Act: -0.1700

Data Index: 1324451 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8655. Min Act: -0.1700

Data Index: 1092434 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8511. Min Act: -0.1700

Data Index: 386268 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8518. Min Act: -0.1699

Data Index: 164788 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8370. Min Act: -0.1700

Data Index: 3949 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7886. Min Act: -0.1475

Data Index: 598039 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8015. Min Act: -0.1665

Data Index: 1276677 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7912. Min Act: -0.1697

Data Index: 1196952 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7891. Min Act: -0.1686

Data Index: 878048 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8041. Min Act: -0.1700

Data Index: 466093 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7570. Min Act: -0.1437

Data Index: 881270 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7594. Min Act: -0.1700

Data Index: 174293 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7670. Min Act: -0.1700

Data Index: 1101951 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7678. Min Act: -0.1700

Data Index: 645189 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7724. Min Act: -0.1700

Data Index: 182309 (C4 (Web Text))

Max Activating Token Index: 767