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

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

Neuron 1203 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: 3.5793. Min Range: -3.5793

Max Act: 3.5793. Min Act: -0.1700

Data Index: 1595775 (Python Code)

Max Activating Token Index: 674

Text #1

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.4027. Min Act: -0.1700

Data Index: 1248310 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.3480. Min Act: -0.1700

Data Index: 211082 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.3344. Min Act: -0.1700

Data Index: 1365484 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.2876. Min Act: -0.1700

Data Index: 1624548 (Python Code)

Max Activating Token Index: 627

Text #5

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.2926. Min Act: -0.1700

Data Index: 1363612 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.2119. Min Act: -0.1700

Data Index: 1505607 (Python Code)

Max Activating Token Index: 762

Text #7

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.2229. Min Act: -0.1700

Data Index: 1433225 (Python Code)

Max Activating Token Index: 766

Text #8

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1888. Min Act: -0.1700

Data Index: 756313 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1880. Min Act: -0.1700

Data Index: 657057 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1856. Min Act: -0.1700

Data Index: 1364716 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1679. Min Act: -0.1700

Data Index: 1517739 (Python Code)

Max Activating Token Index: 841

Text #12

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.2028. Min Act: -0.1700

Data Index: 1038682 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1651. Min Act: -0.1700

Data Index: 1025159 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1933. Min Act: -0.1700

Data Index: 1398181 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1671. Min Act: -0.1700

Data Index: 80614 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1510. Min Act: -0.1700

Data Index: 1389650 (Python Code)

Max Activating Token Index: 889

Text #17

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1396. Min Act: -0.1700

Data Index: 1618617 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1405. Min Act: -0.1700

Data Index: 782516 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 3.5793. Min Range: -3.5793

Max Act: 3.1269. Min Act: -0.1700

Data Index: 1512326 (Python Code)

Max Activating Token Index: 98