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

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

Neuron 977 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: 5.0790. Min Range: -5.0790

Max Act: 5.0790. Min Act: -0.1700

Data Index: 3515 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.9540. Min Act: -0.1700

Data Index: 1280974 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.9852. Min Act: -0.1700

Data Index: 237204 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.8915. Min Act: -0.1700

Data Index: 1158158 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.8915. Min Act: -0.1700

Data Index: 730512 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.7977. Min Act: -0.1700

Data Index: 490719 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.7977. Min Act: -0.1700

Data Index: 818970 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.7352. Min Act: -0.1700

Data Index: 358457 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6727. Min Act: -0.1700

Data Index: 340107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6727. Min Act: -0.1700

Data Index: 975292 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6415. Min Act: -0.1700

Data Index: 403095 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.7040. Min Act: -0.1700

Data Index: 361362 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6727. Min Act: -0.1700

Data Index: 164190 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6727. Min Act: -0.1700

Data Index: 167993 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6727. Min Act: -0.1700

Data Index: 587439 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6727. Min Act: -0.1700

Data Index: 506247 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6727. Min Act: -0.1700

Data Index: 1112428 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6727. Min Act: -0.1700

Data Index: 584243 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6415. Min Act: -0.1700

Data Index: 46744 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 5.0790. Min Range: -5.0790

Max Act: 4.6415. Min Act: -0.1700

Data Index: 151075 (C4 (Web Text))

Max Activating Token Index: 1023