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

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

Neuron 1475 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: 3.1613. Min Range: -3.1613

Max Act: 3.1613. Min Act: -0.1700

Data Index: 593933 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.9719. Min Act: -0.1700

Data Index: 165792 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.9719. Min Act: -0.1696

Data Index: 752956 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.9877. Min Act: -0.1700

Data Index: 370232 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8927. Min Act: -0.1700

Data Index: 1425857 (Python Code)

Max Activating Token Index: 342

Text #5

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.9086. Min Act: -0.1700

Data Index: 310802 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.9086. Min Act: -0.1700

Data Index: 183678 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.9244. Min Act: -0.1700

Data Index: 90057 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8609. Min Act: -0.1700

Data Index: 594878 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8927. Min Act: -0.1700

Data Index: 401172 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8768. Min Act: -0.1700

Data Index: 764981 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8450. Min Act: -0.1700

Data Index: 1309914 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8609. Min Act: -0.1700

Data Index: 723782 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8291. Min Act: -0.1700

Data Index: 629654 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8609. Min Act: -0.1700

Data Index: 842408 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8609. Min Act: -0.1700

Data Index: 1361542 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8132. Min Act: -0.1699

Data Index: 1330407 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8291. Min Act: -0.1700

Data Index: 1563106 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.7973. Min Act: -0.1700

Data Index: 309670 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 3.1613. Min Range: -3.1613

Max Act: 2.8132. Min Act: -0.1700

Data Index: 165264 (C4 (Web Text))

Max Activating Token Index: 426