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

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

Neuron 942 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.3002. Min Act: -0.1700

Data Index: 330753 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.2531. Min Act: -0.1700

Data Index: 806922 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1902. Min Act: -0.1700

Data Index: 934595 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.2059. Min Act: -0.1700

Data Index: 1010798 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1902. Min Act: -0.1700

Data Index: 821542 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1902. Min Act: -0.1700

Data Index: 1170863 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1744. Min Act: -0.1700

Data Index: 1203201 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1902. Min Act: -0.1700

Data Index: 98987 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1744. Min Act: -0.1700

Data Index: 1499544 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1587. Min Act: -0.1700

Data Index: 677217 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1587. Min Act: -0.1700

Data Index: 145184 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1587. Min Act: -0.1700

Data Index: 678530 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1744. Min Act: -0.1700

Data Index: 848886 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1587. Min Act: -0.1700

Data Index: 328999 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1587. Min Act: -0.1700

Data Index: 69931 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1430. Min Act: -0.1700

Data Index: 1236247 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1430. Min Act: -0.1700

Data Index: 1215343 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1587. Min Act: -0.1700

Data Index: 1092384 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1430. Min Act: -0.1700

Data Index: 734947 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1430. Min Act: -0.1700

Data Index: 625606 (C4 (Web Text))

Max Activating Token Index: 114