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

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

Neuron 345 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: 3.5768. Min Range: -3.5768

Max Act: 3.5768. Min Act: -0.1700

Data Index: 1560849 (Python Code)

Max Activating Token Index: 725

Text #1

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.5488. Min Act: -0.1700

Data Index: 1480716 (Python Code)

Max Activating Token Index: 335

Text #2

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.5202. Min Act: -0.1700

Data Index: 1391660 (Python Code)

Max Activating Token Index: 414

Text #3

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.5062. Min Act: -0.1700

Data Index: 1462622 (Python Code)

Max Activating Token Index: 942

Text #4

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.5004. Min Act: -0.1700

Data Index: 1414339 (Python Code)

Max Activating Token Index: 283

Text #5

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.5047. Min Act: -0.1700

Data Index: 1646843 (Python Code)

Max Activating Token Index: 140

Text #6

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4744. Min Act: -0.1700

Data Index: 1385048 (Python Code)

Max Activating Token Index: 150

Text #7

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4863. Min Act: -0.1699

Data Index: 1531240 (Python Code)

Max Activating Token Index: 710

Text #8

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4850. Min Act: -0.1700

Data Index: 1459369 (Python Code)

Max Activating Token Index: 249

Text #9

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4876. Min Act: -0.1700

Data Index: 1600448 (Python Code)

Max Activating Token Index: 184

Text #10

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4778. Min Act: -0.1700

Data Index: 1619251 (Python Code)

Max Activating Token Index: 831

Text #11

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4532. Min Act: -0.1700

Data Index: 1374087 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4404. Min Act: -0.1700

Data Index: 1626308 (Python Code)

Max Activating Token Index: 348

Text #13

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4460. Min Act: -0.1700

Data Index: 1581000 (Python Code)

Max Activating Token Index: 302

Text #14

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4374. Min Act: -0.1700

Data Index: 1405081 (Python Code)

Max Activating Token Index: 775

Text #15

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4508. Min Act: -0.1700

Data Index: 1509907 (Python Code)

Max Activating Token Index: 904

Text #16

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4639. Min Act: -0.1700

Data Index: 1363833 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4543. Min Act: -0.1700

Data Index: 1502023 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4507. Min Act: -0.1700

Data Index: 790679 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 3.5768. Min Range: -3.5768

Max Act: 3.4550. Min Act: -0.1700

Data Index: 1505944 (Python Code)

Max Activating Token Index: 826