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

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

Neuron 577 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: 3.1075. Min Range: -3.1075

Max Act: 3.1058. Min Act: -0.1700

Data Index: 1518595 (Python Code)

Max Activating Token Index: 324

Text #1

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.1075. Min Act: -0.1700

Data Index: 1566031 (Python Code)

Max Activating Token Index: 440

Text #2

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0992. Min Act: -0.1700

Data Index: 1420392 (Python Code)

Max Activating Token Index: 971

Text #3

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0986. Min Act: -0.1700

Data Index: 1220458 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0680. Min Act: -0.1700

Data Index: 1571423 (Python Code)

Max Activating Token Index: 314

Text #5

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0590. Min Act: -0.1700

Data Index: 1624944 (Python Code)

Max Activating Token Index: 703

Text #6

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0599. Min Act: -0.1700

Data Index: 1503863 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0681. Min Act: -0.1700

Data Index: 1469131 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0670. Min Act: -0.1700

Data Index: 1445883 (Python Code)

Max Activating Token Index: 234

Text #9

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0671. Min Act: -0.1700

Data Index: 1600063 (Python Code)

Max Activating Token Index: 182

Text #10

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0722. Min Act: -0.1700

Data Index: 1615144 (Python Code)

Max Activating Token Index: 833

Text #11

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0578. Min Act: -0.1700

Data Index: 1655650 (Python Code)

Max Activating Token Index: 324

Text #12

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0516. Min Act: -0.1700

Data Index: 1431565 (Python Code)

Max Activating Token Index: 962

Text #13

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0435. Min Act: -0.1700

Data Index: 1580962 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0398. Min Act: -0.1700

Data Index: 1381336 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0463. Min Act: -0.1700

Data Index: 1440619 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0462. Min Act: -0.1700

Data Index: 1644398 (Python Code)

Max Activating Token Index: 255

Text #17

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0478. Min Act: -0.1700

Data Index: 1617654 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0261. Min Act: -0.1700

Data Index: 1593479 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.0364. Min Act: -0.1700

Data Index: 1605406 (Python Code)

Max Activating Token Index: 352