Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1691 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.2059. Min Range: -4.2059

Max Act: 4.2059. Min Act: -0.1700

Data Index: 924625 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 4.2059. Min Range: -4.2059

Max Act: 4.0809. Min Act: -0.1700

Data Index: 1035226 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 4.2059. Min Range: -4.2059

Max Act: 4.0809. Min Act: -0.1700

Data Index: 720998 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 4.2059. Min Range: -4.2059

Max Act: 4.0183. Min Act: -0.1700

Data Index: 57706 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9871. Min Act: -0.1700

Data Index: 1564776 (Python Code)

Max Activating Token Index: 1004

Text #5

Max Range: 4.2059. Min Range: -4.2059

Max Act: 4.0183. Min Act: -0.1700

Data Index: 1302388 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9558. Min Act: -0.1700

Data Index: 80504 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9245. Min Act: -0.1700

Data Index: 1125124 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9558. Min Act: -0.1700

Data Index: 1565758 (Python Code)

Max Activating Token Index: 928

Text #9

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9245. Min Act: -0.1700

Data Index: 970128 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9558. Min Act: -0.1700

Data Index: 483364 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9558. Min Act: -0.1700

Data Index: 379334 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.8933. Min Act: -0.1700

Data Index: 242865 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9245. Min Act: -0.1700

Data Index: 306257 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9245. Min Act: -0.1700

Data Index: 1047439 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9245. Min Act: -0.1700

Data Index: 648113 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.8933. Min Act: -0.1700

Data Index: 692350 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.8620. Min Act: -0.1700

Data Index: 990219 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.9245. Min Act: -0.1700

Data Index: 1208537 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 4.2059. Min Range: -4.2059

Max Act: 3.8620. Min Act: -0.1700

Data Index: 84651 (C4 (Web Text))

Max Activating Token Index: 81