Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 868 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7474. Min Act: -0.1700

Data Index: 1172785 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7005. Min Act: -0.1700

Data Index: 534993 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.7005. Min Act: -0.1700

Data Index: 335112 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6848. Min Act: -0.1700

Data Index: 377584 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6535. Min Act: -0.1700

Data Index: 697135 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6692. Min Act: -0.1700

Data Index: 903666 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6535. Min Act: -0.1700

Data Index: 339541 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6535. Min Act: -0.1700

Data Index: 695286 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6379. Min Act: -0.1700

Data Index: 422686 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.5596. Min Act: -0.1700

Data Index: 1226577 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.6222. Min Act: -0.1700

Data Index: 721168 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.5753. Min Act: -0.1700

Data Index: 31051 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.5753. Min Act: -0.1700

Data Index: 570796 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.5283. Min Act: -0.1700

Data Index: 755616 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.5439. Min Act: -0.1700

Data Index: 1047463 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.5909. Min Act: -0.1700

Data Index: 806621 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.5753. Min Act: -0.1700

Data Index: 970794 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.4969. Min Act: -0.1700

Data Index: 702650 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.4969. Min Act: -0.1700

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 3.7474. Min Range: -3.7474

Max Act: 3.4969. Min Act: -0.1700

Data Index: 1186356 (C4 (Web Text))

Max Activating Token Index: 944