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

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

Neuron 1653 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: 3.3418. Min Range: -3.3418

Max Act: 3.3418. Min Act: -0.1700

Data Index: 1508040 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.3104. Min Act: -0.1700

Data Index: 1428839 (Python Code)

Max Activating Token Index: 925

Text #2

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.3104. Min Act: -0.1700

Data Index: 1488589 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.3261. Min Act: -0.1700

Data Index: 1552058 (Python Code)

Max Activating Token Index: 801

Text #4

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.3104. Min Act: -0.1700

Data Index: 1369719 (Python Code)

Max Activating Token Index: 1004

Text #5

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2947. Min Act: -0.1700

Data Index: 1414247 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2790. Min Act: -0.1700

Data Index: 1552858 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2947. Min Act: -0.1700

Data Index: 1464200 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2476. Min Act: -0.1700

Data Index: 1528340 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2319. Min Act: -0.1700

Data Index: 1471421 (Python Code)

Max Activating Token Index: 857

Text #10

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2476. Min Act: -0.1700

Data Index: 1566698 (Python Code)

Max Activating Token Index: 962

Text #11

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2633. Min Act: -0.1700

Data Index: 1462736 (Python Code)

Max Activating Token Index: 287

Text #12

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2633. Min Act: -0.1700

Data Index: 1603845 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2319. Min Act: -0.1700

Data Index: 1500108 (Python Code)

Max Activating Token Index: 952

Text #14

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2633. Min Act: -0.1700

Data Index: 1530217 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2004. Min Act: -0.1700

Data Index: 1551703 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2004. Min Act: -0.1700

Data Index: 1382169 (Python Code)

Max Activating Token Index: 751

Text #17

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.1532. Min Act: -0.1700

Data Index: 1403382 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.2004. Min Act: -0.1700

Data Index: 1546667 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 3.3418. Min Range: -3.3418

Max Act: 3.1847. Min Act: -0.1700

Data Index: 1618252 (Python Code)

Max Activating Token Index: 419