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

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

Neuron 947 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: 3.9491. Min Range: -3.9491

Max Act: 3.9491. Min Act: -0.1699

Data Index: 1625076 (Python Code)

Max Activating Token Index: 570

Text #1

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.9409. Min Act: -0.1700

Data Index: 1511791 (Python Code)

Max Activating Token Index: 606

Text #2

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.8996. Min Act: -0.1700

Data Index: 1592550 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.8160. Min Act: -0.1697

Data Index: 606072 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.8115. Min Act: -0.1700

Data Index: 1648267 (Python Code)

Max Activating Token Index: 625

Text #5

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.8381. Min Act: -0.1700

Data Index: 1597951 (Python Code)

Max Activating Token Index: 827

Text #6

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.8106. Min Act: -0.1700

Data Index: 1392297 (Python Code)

Max Activating Token Index: 625

Text #7

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.8715. Min Act: -0.1699

Data Index: 1542722 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.7839. Min Act: -0.1700

Data Index: 480205 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.7796. Min Act: -0.1700

Data Index: 1443190 (Python Code)

Max Activating Token Index: 849

Text #10

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.7853. Min Act: -0.1700

Data Index: 1539827 (Python Code)

Max Activating Token Index: 577

Text #11

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.7767. Min Act: -0.1699

Data Index: 1496156 (Python Code)

Max Activating Token Index: 936

Text #12

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.7637. Min Act: -0.1685

Data Index: 1571017 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.7637. Min Act: -0.1700

Data Index: 455587 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.7264. Min Act: -0.1700

Data Index: 1446735 (Python Code)

Max Activating Token Index: 521

Text #15

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.6984. Min Act: -0.1700

Data Index: 1409796 (Python Code)

Max Activating Token Index: 1003

Text #16

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.6988. Min Act: -0.1700

Data Index: 1506532 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.7133. Min Act: -0.1699

Data Index: 1508205 (Python Code)

Max Activating Token Index: 437

Text #18

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.6865. Min Act: -0.1700

Data Index: 1528186 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 3.9491. Min Range: -3.9491

Max Act: 3.7235. Min Act: -0.1700

Data Index: 1564985 (Python Code)

Max Activating Token Index: 723