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

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

Neuron 1089 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.2482. Min Range: -8.2482

Max Act: 8.2482. Min Act: -0.1700

Data Index: 433524 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 8.2482. Min Range: -8.2482

Max Act: 8.0607. Min Act: -0.1698

Data Index: 600294 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.9357. Min Act: -0.1700

Data Index: 1281225 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.8732. Min Act: -0.1699

Data Index: 176607 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.6544. Min Act: -0.1700

Data Index: 89861 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.6544. Min Act: -0.1700

Data Index: 551680 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.6232. Min Act: -0.1699

Data Index: 1326056 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.5294. Min Act: -0.1690

Data Index: 1156237 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.5919. Min Act: -0.1700

Data Index: 905401 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.6232. Min Act: -0.1700

Data Index: 1205428 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.6232. Min Act: -0.1700

Data Index: 684503 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.5607. Min Act: -0.1700

Data Index: 565371 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.4669. Min Act: -0.1699

Data Index: 437314 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.4982. Min Act: -0.1700

Data Index: 1323938 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.5294. Min Act: -0.1694

Data Index: 112387 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.5294. Min Act: -0.1700

Data Index: 846043 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.4669. Min Act: -0.1700

Data Index: 1345927 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.4982. Min Act: -0.1698

Data Index: 1148805 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.4982. Min Act: -0.1700

Data Index: 366797 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 8.2482. Min Range: -8.2482

Max Act: 7.4044. Min Act: -0.1700

Data Index: 191326 (C4 (Web Text))

Max Activating Token Index: 597