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

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

Neuron 1253 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: 5.2359. Min Range: -5.2359

Max Act: 5.2359. Min Act: -0.1700

Data Index: 1026222 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.2359. Min Act: -0.1700

Data Index: 1084370 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.1734. Min Act: -0.1700

Data Index: 617626 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.1734. Min Act: -0.1700

Data Index: 45886 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.1422. Min Act: -0.1699

Data Index: 927528 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.1109. Min Act: -0.1700

Data Index: 945959 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.0797. Min Act: -0.1700

Data Index: 1261827 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.1109. Min Act: -0.1700

Data Index: 128267 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.0484. Min Act: -0.1700

Data Index: 884769 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.0172. Min Act: -0.1700

Data Index: 784040 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 5.2359. Min Range: -5.2359

Max Act: 4.9859. Min Act: -0.1700

Data Index: 1204535 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 5.2359. Min Range: -5.2359

Max Act: 5.0172. Min Act: -0.1700

Data Index: 877634 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 5.2359. Min Range: -5.2359

Max Act: 4.9859. Min Act: -0.1700

Data Index: 29044 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 5.2359. Min Range: -5.2359

Max Act: 4.9547. Min Act: -0.1700

Data Index: 200665 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 5.2359. Min Range: -5.2359

Max Act: 4.8922. Min Act: -0.1700

Data Index: 1082435 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 5.2359. Min Range: -5.2359

Max Act: 4.9859. Min Act: -0.1700

Data Index: 541339 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 5.2359. Min Range: -5.2359

Max Act: 4.9859. Min Act: -0.1700

Data Index: 363950 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 5.2359. Min Range: -5.2359

Max Act: 4.8922. Min Act: -0.1700

Data Index: 1213864 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 5.2359. Min Range: -5.2359

Max Act: 4.9859. Min Act: -0.1700

Data Index: 156834 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 5.2359. Min Range: -5.2359

Max Act: 4.9234. Min Act: -0.1700

Data Index: 700387 (C4 (Web Text))

Max Activating Token Index: 616