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

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

Neuron 1842 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.8539. Min Act: -0.1700

Data Index: 797603 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.8226. Min Act: -0.1700

Data Index: 1276541 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.8539. Min Act: -0.1700

Data Index: 345366 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7601. Min Act: -0.1700

Data Index: 1269185 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7288. Min Act: -0.1700

Data Index: 184902 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7601. Min Act: -0.1700

Data Index: 958517 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7913. Min Act: -0.1700

Data Index: 1151738 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7288. Min Act: -0.1700

Data Index: 605466 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6662. Min Act: -0.1700

Data Index: 850753 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6662. Min Act: -0.1700

Data Index: 1084042 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6975. Min Act: -0.1700

Data Index: 934806 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6975. Min Act: -0.1700

Data Index: 387641 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6349. Min Act: -0.1700

Data Index: 599467 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6662. Min Act: -0.1700

Data Index: 895464 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6349. Min Act: -0.1700

Data Index: 543575 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6036. Min Act: -0.1700

Data Index: 1057949 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.5722. Min Act: -0.1700

Data Index: 458385 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6036. Min Act: -0.1700

Data Index: 129537 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6036. Min Act: -0.1700

Data Index: 1050308 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6349. Min Act: -0.1700

Data Index: 1083199 (C4 (Web Text))

Max Activating Token Index: 713