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

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

Neuron 447 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: 4.1998. Min Range: -4.1998

Max Act: 4.1998. Min Act: -0.1683

Data Index: 1458544 (Python Code)

Max Activating Token Index: 230

Text #1

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.1604. Min Act: -0.1699

Data Index: 728627 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.1727. Min Act: -0.1697

Data Index: 1370265 (Python Code)

Max Activating Token Index: 695

Text #3

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.1239. Min Act: -0.1339

Data Index: 1586529 (Python Code)

Max Activating Token Index: 758

Text #4

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0649. Min Act: -0.1655

Data Index: 1366701 (Python Code)

Max Activating Token Index: 250

Text #5

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0837. Min Act: -0.1339

Data Index: 1382768 (Python Code)

Max Activating Token Index: 293

Text #6

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0444. Min Act: -0.1695

Data Index: 985870 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0506. Min Act: -0.1699

Data Index: 1548352 (Python Code)

Max Activating Token Index: 674

Text #8

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0367. Min Act: -0.1684

Data Index: 1643211 (Python Code)

Max Activating Token Index: 912

Text #9

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0397. Min Act: -0.1641

Data Index: 1310309 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0184. Min Act: -0.1700

Data Index: 1360458 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0027. Min Act: -0.1699

Data Index: 1377077 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0090. Min Act: -0.1700

Data Index: 1299538 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 4.1998. Min Range: -4.1998

Max Act: 4.0109. Min Act: -0.1699

Data Index: 1175199 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 4.1998. Min Range: -4.1998

Max Act: 3.9591. Min Act: -0.1700

Data Index: 1647838 (Python Code)

Max Activating Token Index: 844

Text #15

Max Range: 4.1998. Min Range: -4.1998

Max Act: 3.9656. Min Act: -0.1339

Data Index: 1630481 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 4.1998. Min Range: -4.1998

Max Act: 3.9718. Min Act: -0.1700

Data Index: 239393 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 4.1998. Min Range: -4.1998

Max Act: 3.9605. Min Act: -0.1339

Data Index: 15346 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 4.1998. Min Range: -4.1998

Max Act: 3.9860. Min Act: -0.1700

Data Index: 1551123 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 4.1998. Min Range: -4.1998

Max Act: 3.9782. Min Act: -0.1699

Data Index: 1416746 (Python Code)

Max Activating Token Index: 943