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

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

Neuron 570 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: 3.3708. Min Range: -3.3708

Max Act: 3.3708. Min Act: -0.1700

Data Index: 196069 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.3394. Min Act: -0.1700

Data Index: 805164 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.3394. Min Act: -0.1700

Data Index: 612522 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.3080. Min Act: -0.1700

Data Index: 566486 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.2766. Min Act: -0.1700

Data Index: 713096 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.2766. Min Act: -0.1700

Data Index: 465451 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.2295. Min Act: -0.1700

Data Index: 880608 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.2452. Min Act: -0.1700

Data Index: 381325 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.2295. Min Act: -0.1700

Data Index: 1144297 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.2295. Min Act: -0.1700

Data Index: 297871 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1980. Min Act: -0.1700

Data Index: 810979 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1823. Min Act: -0.1700

Data Index: 500854 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1823. Min Act: -0.1700

Data Index: 1220527 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1980. Min Act: -0.1700

Data Index: 863903 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1823. Min Act: -0.1700

Data Index: 259476 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1980. Min Act: -0.1700

Data Index: 305598 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1665. Min Act: -0.1700

Data Index: 595122 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1665. Min Act: -0.1700

Data Index: 1334780 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1823. Min Act: -0.1700

Data Index: 734878 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.3708. Min Range: -3.3708

Max Act: 3.1665. Min Act: -0.1700

Data Index: 480920 (C4 (Web Text))

Max Activating Token Index: 390