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

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

Neuron 1621 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.5467. Min Act: -0.1699

Data Index: 754384 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.4841. Min Act: -0.1700

Data Index: 431894 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.5154. Min Act: -0.1700

Data Index: 391619 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3900. Min Act: -0.1700

Data Index: 523561 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3743. Min Act: -0.1700

Data Index: 831877 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3429. Min Act: -0.1700

Data Index: 704513 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3115. Min Act: -0.1700

Data Index: 812959 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3115. Min Act: -0.1700

Data Index: 1156213 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3115. Min Act: -0.1700

Data Index: 1358370 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2958. Min Act: -0.1700

Data Index: 136915 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2958. Min Act: -0.1700

Data Index: 618268 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2644. Min Act: -0.1700

Data Index: 101858 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2487. Min Act: -0.1700

Data Index: 591285 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2487. Min Act: -0.1700

Data Index: 1041663 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2172. Min Act: -0.1700

Data Index: 297849 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2330. Min Act: -0.1700

Data Index: 549744 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2487. Min Act: -0.1700

Data Index: 144320 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2330. Min Act: -0.1700

Data Index: 1024788 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2487. Min Act: -0.1700

Data Index: 527098 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2172. Min Act: -0.1700

Data Index: 890906 (C4 (Web Text))

Max Activating Token Index: 565