Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 528 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.4776. Min Act: -0.1700

Data Index: 27259 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.4464. Min Act: -0.1700

Data Index: 997290 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.3839. Min Act: -0.1700

Data Index: 607276 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.4151. Min Act: -0.1700

Data Index: 1323802 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.3526. Min Act: -0.1700

Data Index: 470691 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.3526. Min Act: -0.1700

Data Index: 907998 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.3526. Min Act: -0.1700

Data Index: 805137 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.2589. Min Act: -0.1700

Data Index: 787147 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.2589. Min Act: -0.1700

Data Index: 775413 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.2276. Min Act: -0.1700

Data Index: 707461 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.2276. Min Act: -0.1700

Data Index: 992728 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.3214. Min Act: -0.1700

Data Index: 1026780 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.2589. Min Act: -0.1700

Data Index: 691600 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.3214. Min Act: -0.1700

Data Index: 352904 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.2276. Min Act: -0.1700

Data Index: 1247579 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.1964. Min Act: -0.1700

Data Index: 1318819 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.1651. Min Act: -0.1700

Data Index: 288804 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.1964. Min Act: -0.1700

Data Index: 784156 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.1339. Min Act: -0.1700

Data Index: 235639 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 5.4776. Min Range: -5.4776

Max Act: 5.1339. Min Act: -0.1700

Data Index: 291426 (C4 (Web Text))

Max Activating Token Index: 653