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

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

Neuron 973 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: 3.2755. Min Range: -3.2755

Max Act: 3.2598. Min Act: -0.1700

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.2441. Min Act: -0.1700

Data Index: 226808 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.2755. Min Act: -0.1700

Data Index: 566740 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.2441. Min Act: -0.1700

Data Index: 154513 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.2441. Min Act: -0.1700

Data Index: 1129701 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1340. Min Act: -0.1700

Data Index: 682078 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1969. Min Act: -0.1700

Data Index: 689280 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1182. Min Act: -0.1700

Data Index: 1381711 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0709. Min Act: -0.1700

Data Index: 888456 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0867. Min Act: -0.1700

Data Index: 451977 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0709. Min Act: -0.1700

Data Index: 975214 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1182. Min Act: -0.1700

Data Index: 1121970 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0709. Min Act: -0.1700

Data Index: 858294 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0867. Min Act: -0.1700

Data Index: 464024 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1024. Min Act: -0.1700

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0867. Min Act: -0.1700

Data Index: 25521 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0867. Min Act: -0.1700

Data Index: 314490 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0709. Min Act: -0.1700

Data Index: 25593 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0867. Min Act: -0.1700

Data Index: 79265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0551. Min Act: -0.1700

Data Index: 801663 (C4 (Web Text))

Max Activating Token Index: 395