Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1861 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.1584. Min Range: -5.1584

Max Act: 5.1584. Min Act: -0.1628

Data Index: 334500 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 5.1584. Min Range: -5.1584

Max Act: 5.1151. Min Act: -0.1699

Data Index: 249202 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.9953. Min Act: -0.1700

Data Index: 1567795 (Python Code)

Max Activating Token Index: 963

Text #3

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.9885. Min Act: -0.0617

Data Index: 143100 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 5.1584. Min Range: -5.1584

Max Act: 5.0096. Min Act: -0.1700

Data Index: 1059276 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.9844. Min Act: -0.1694

Data Index: 1442496 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.9397. Min Act: -0.1676

Data Index: 359610 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.9782. Min Act: -0.1621

Data Index: 504591 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.9457. Min Act: -0.1645

Data Index: 760837 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.9536. Min Act: -0.1700

Data Index: 513091 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.9199. Min Act: -0.1640

Data Index: 515464 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.8983. Min Act: -0.1700

Data Index: 553084 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.8720. Min Act: -0.1700

Data Index: 527887 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.8873. Min Act: -0.1697

Data Index: 1029598 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.8500. Min Act: -0.1698

Data Index: 1378271 (Python Code)

Max Activating Token Index: 295

Text #15

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.8562. Min Act: -0.1675

Data Index: 1595020 (Python Code)

Max Activating Token Index: 606

Text #16

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.8505. Min Act: -0.1700

Data Index: 368168 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.8516. Min Act: -0.1699

Data Index: 78620 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.8376. Min Act: -0.1699

Data Index: 42402 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 5.1584. Min Range: -5.1584

Max Act: 4.8659. Min Act: -0.1700

Data Index: 420475 (C4 (Web Text))

Max Activating Token Index: 312