Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1381 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.4513. Min Act: -0.1700

Data Index: 907777 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3729. Min Act: -0.1700

Data Index: 1551851 (Python Code)

Max Activating Token Index: 1006

Text #2

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.2944. Min Act: -0.1700

Data Index: 1526673 (Python Code)

Max Activating Token Index: 799

Text #3

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3258. Min Act: -0.1700

Data Index: 1450676 (Python Code)

Max Activating Token Index: 658

Text #4

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.2944. Min Act: -0.1700

Data Index: 1577327 (Python Code)

Max Activating Token Index: 814

Text #5

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3572. Min Act: -0.1700

Data Index: 1404596 (Python Code)

Max Activating Token Index: 998

Text #6

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.2787. Min Act: -0.1700

Data Index: 1564524 (Python Code)

Max Activating Token Index: 916

Text #7

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3258. Min Act: -0.1700

Data Index: 1464993 (Python Code)

Max Activating Token Index: 773

Text #8

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3415. Min Act: -0.1700

Data Index: 1374842 (Python Code)

Max Activating Token Index: 1001

Text #9

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3415. Min Act: -0.1700

Data Index: 1400038 (Python Code)

Max Activating Token Index: 994

Text #10

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3258. Min Act: -0.1700

Data Index: 1564619 (Python Code)

Max Activating Token Index: 743

Text #11

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3729. Min Act: -0.1700

Data Index: 1379658 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3258. Min Act: -0.1700

Data Index: 1488944 (Python Code)

Max Activating Token Index: 998

Text #13

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3258. Min Act: -0.1700

Data Index: 1549717 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3415. Min Act: -0.1700

Data Index: 1434916 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.2944. Min Act: -0.1700

Data Index: 1410591 (Python Code)

Max Activating Token Index: 699

Text #16

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.2315. Min Act: -0.1700

Data Index: 1509359 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.2630. Min Act: -0.1700

Data Index: 1463295 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3101. Min Act: -0.1700

Data Index: 1564636 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3415. Min Act: -0.1700

Data Index: 1561285 (Python Code)

Max Activating Token Index: 791