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

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

Neuron 1660 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: 3.4448. Min Range: -3.4448

Max Act: 3.4448. Min Act: -0.1700

Data Index: 747715 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.4448. Min Act: -0.1700

Data Index: 409611 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.3664. Min Act: -0.1700

Data Index: 1348100 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.3821. Min Act: -0.1700

Data Index: 133044 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.3821. Min Act: -0.1700

Data Index: 964509 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.3193. Min Act: -0.1700

Data Index: 830760 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.3036. Min Act: -0.1700

Data Index: 1173415 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.3036. Min Act: -0.1700

Data Index: 1287626 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2722. Min Act: -0.1700

Data Index: 1357048 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.3036. Min Act: -0.1700

Data Index: 827116 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2722. Min Act: -0.1700

Data Index: 243927 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2879. Min Act: -0.1700

Data Index: 796027 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2565. Min Act: -0.1700

Data Index: 510821 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2722. Min Act: -0.1700

Data Index: 1318294 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2565. Min Act: -0.1700

Data Index: 724074 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2722. Min Act: -0.1700

Data Index: 52888 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2879. Min Act: -0.1700

Data Index: 1191970 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2722. Min Act: -0.1700

Data Index: 159578 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2565. Min Act: -0.1700

Data Index: 1127030 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 3.4448. Min Range: -3.4448

Max Act: 3.2565. Min Act: -0.1700

Data Index: 68904 (C4 (Web Text))

Max Activating Token Index: 656