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

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

Neuron 349 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: 3.9080. Min Range: -3.9080

Max Act: 3.9080. Min Act: -0.1700

Data Index: 178479 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.9080. Min Act: -0.1700

Data Index: 143821 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.8454. Min Act: -0.1700

Data Index: 673778 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.7359. Min Act: -0.1700

Data Index: 66553 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.7203. Min Act: -0.1700

Data Index: 1221284 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.7203. Min Act: -0.1700

Data Index: 642495 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.6733. Min Act: -0.1700

Data Index: 1229777 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.6577. Min Act: -0.1700

Data Index: 700571 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.5951. Min Act: -0.1700

Data Index: 125626 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.6420. Min Act: -0.1700

Data Index: 1087800 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.6577. Min Act: -0.1700

Data Index: 1320193 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.6420. Min Act: -0.1700

Data Index: 394312 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.6264. Min Act: -0.1700

Data Index: 1000217 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.6264. Min Act: -0.1700

Data Index: 730287 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.6420. Min Act: -0.1700

Data Index: 1292955 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.5481. Min Act: -0.1700

Data Index: 9369 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.5794. Min Act: -0.1700

Data Index: 585978 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.5951. Min Act: -0.1700

Data Index: 757196 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.5481. Min Act: -0.1700

Data Index: 814547 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 3.9080. Min Range: -3.9080

Max Act: 3.5951. Min Act: -0.1700

Data Index: 327616 (C4 (Web Text))

Max Activating Token Index: 138