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

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

Neuron 266 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.5078. Min Act: -0.1700

Data Index: 690170 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3981. Min Act: -0.1700

Data Index: 925712 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3510. Min Act: -0.1700

Data Index: 505300 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3667. Min Act: -0.1700

Data Index: 715068 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3196. Min Act: -0.1700

Data Index: 704039 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3667. Min Act: -0.1700

Data Index: 940206 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3510. Min Act: -0.1700

Data Index: 1326841 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3510. Min Act: -0.1700

Data Index: 207054 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3196. Min Act: -0.1700

Data Index: 477020 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.2882. Min Act: -0.1700

Data Index: 64069 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3196. Min Act: -0.1700

Data Index: 625009 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3039. Min Act: -0.1700

Data Index: 625166 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3039. Min Act: -0.1700

Data Index: 544032 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.2882. Min Act: -0.1700

Data Index: 393555 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.2882. Min Act: -0.1700

Data Index: 828732 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3196. Min Act: -0.1700

Data Index: 196345 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3039. Min Act: -0.1700

Data Index: 1152808 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3039. Min Act: -0.1700

Data Index: 1134289 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.2725. Min Act: -0.1700

Data Index: 288113 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 3.5078. Min Range: -3.5078

Max Act: 3.3196. Min Act: -0.1700

Data Index: 295513 (C4 (Web Text))

Max Activating Token Index: 805