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

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

Neuron 861 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1326220 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.1295. Min Act: -0.1700

Data Index: 4971 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.1138. Min Act: -0.1700

Data Index: 982648 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0822. Min Act: -0.1700

Data Index: 1211672 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0822. Min Act: -0.1700

Data Index: 489993 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0822. Min Act: -0.1700

Data Index: 984203 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0822. Min Act: -0.1700

Data Index: 1216116 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0665. Min Act: -0.1700

Data Index: 601119 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0980. Min Act: -0.1700

Data Index: 251593 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0822. Min Act: -0.1700

Data Index: 1351259 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0507. Min Act: -0.1700

Data Index: 47960 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0349. Min Act: -0.1700

Data Index: 35465 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0349. Min Act: -0.1700

Data Index: 1345098 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0507. Min Act: -0.1700

Data Index: 1026710 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0507. Min Act: -0.1700

Data Index: 1252153 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0349. Min Act: -0.1700

Data Index: 1289883 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0191. Min Act: -0.1700

Data Index: 950337 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0191. Min Act: -0.1700

Data Index: 1073034 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0033. Min Act: -0.1700

Data Index: 1084438 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 3.1453. Min Range: -3.1453

Max Act: 3.0349. Min Act: -0.1700

Data Index: 1120306 (C4 (Web Text))

Max Activating Token Index: 397