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

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

Neuron 1263 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: 3.9528. Min Range: -3.9528

Max Act: 3.9528. Min Act: -0.1699

Data Index: 300492 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.9463. Min Act: -0.1700

Data Index: 1557230 (Python Code)

Max Activating Token Index: 897

Text #2

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.9213. Min Act: -0.1700

Data Index: 130028 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.9242. Min Act: -0.1700

Data Index: 1591728 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.9282. Min Act: -0.1700

Data Index: 1498492 (Python Code)

Max Activating Token Index: 355

Text #5

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.9005. Min Act: -0.1699

Data Index: 1625845 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8679. Min Act: -0.1698

Data Index: 1493578 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8420. Min Act: -0.1700

Data Index: 1433581 (Python Code)

Max Activating Token Index: 543

Text #8

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8145. Min Act: -0.1700

Data Index: 1379240 (Python Code)

Max Activating Token Index: 521

Text #9

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8212. Min Act: -0.1700

Data Index: 1592413 (Python Code)

Max Activating Token Index: 695

Text #10

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8605. Min Act: -0.1700

Data Index: 1596401 (Python Code)

Max Activating Token Index: 656

Text #11

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8700. Min Act: -0.1700

Data Index: 1370406 (Python Code)

Max Activating Token Index: 674

Text #12

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8209. Min Act: -0.1700

Data Index: 199822 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8528. Min Act: -0.1700

Data Index: 635796 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8712. Min Act: -0.1700

Data Index: 843443 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8036. Min Act: -0.1697

Data Index: 1069266 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.7643. Min Act: -0.1699

Data Index: 1450369 (Python Code)

Max Activating Token Index: 786

Text #17

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.7608. Min Act: -0.1699

Data Index: 1532675 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8044. Min Act: -0.1700

Data Index: 516171 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.7594. Min Act: -0.1700

Data Index: 1144766 (C4 (Web Text))

Max Activating Token Index: 829