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

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

Neuron 1145 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: 3.3005. Min Range: -3.3005

Max Act: 3.3005. Min Act: -0.1700

Data Index: 929448 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.1905. Min Act: -0.1700

Data Index: 1103967 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.1275. Min Act: -0.1700

Data Index: 856400 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.1275. Min Act: -0.1700

Data Index: 265518 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.1275. Min Act: -0.1700

Data Index: 1339300 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0960. Min Act: -0.1700

Data Index: 1252774 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0802. Min Act: -0.1700

Data Index: 128029 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0644. Min Act: -0.1700

Data Index: 1166885 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0802. Min Act: -0.1700

Data Index: 377915 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0328. Min Act: -0.1700

Data Index: 160120 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0486. Min Act: -0.1700

Data Index: 726514 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0486. Min Act: -0.1700

Data Index: 118006 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0328. Min Act: -0.1700

Data Index: 115043 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0170. Min Act: -0.1700

Data Index: 186622 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0170. Min Act: -0.1700

Data Index: 638618 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0170. Min Act: -0.1700

Data Index: 1213776 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0486. Min Act: -0.1700

Data Index: 77601 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0170. Min Act: -0.1700

Data Index: 927582 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0328. Min Act: -0.1700

Data Index: 594 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 3.3005. Min Range: -3.3005

Max Act: 3.0170. Min Act: -0.1700

Data Index: 724438 (C4 (Web Text))

Max Activating Token Index: 610