Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 74 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0858. Min Act: -0.1699

Data Index: 419467 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0528. Min Act: -0.1699

Data Index: 179897 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0503. Min Act: -0.1687

Data Index: 51836 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0451. Min Act: -0.1700

Data Index: 67796 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0353. Min Act: -0.1694

Data Index: 336970 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0150. Min Act: -0.1700

Data Index: 1035911 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0145. Min Act: -0.1699

Data Index: 1168933 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0274. Min Act: -0.1700

Data Index: 802078 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0112. Min Act: -0.1699

Data Index: 754188 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0068. Min Act: -0.1695

Data Index: 640059 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.9969. Min Act: -0.1699

Data Index: 198936 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 3.0858. Min Range: -3.0858

Max Act: 3.0032. Min Act: -0.1696

Data Index: 1287955 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.9713. Min Act: -0.1696

Data Index: 1265440 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.9775. Min Act: -0.1699

Data Index: 1198324 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.9388. Min Act: -0.1656

Data Index: 828660 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.9532. Min Act: -0.1700

Data Index: 786388 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.9321. Min Act: -0.1700

Data Index: 1291943 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.9187. Min Act: -0.1700

Data Index: 1313343 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.9240. Min Act: -0.1698

Data Index: 447150 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.9042. Min Act: -0.1700

Data Index: 682830 (C4 (Web Text))

Max Activating Token Index: 867