Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 260 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2896. Min Act: -0.1699

Data Index: 200833 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2896. Min Act: -0.1700

Data Index: 54607 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1952. Min Act: -0.1700

Data Index: 1085806 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1952. Min Act: -0.1700

Data Index: 455372 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1638. Min Act: -0.1700

Data Index: 98332 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1952. Min Act: -0.1700

Data Index: 213692 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1638. Min Act: -0.1700

Data Index: 61371 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1007. Min Act: -0.1700

Data Index: 1206145 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1323. Min Act: -0.1700

Data Index: 1188939 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1638. Min Act: -0.1700

Data Index: 233678 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1323. Min Act: -0.1700

Data Index: 1259009 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1952. Min Act: -0.1700

Data Index: 927586 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1323. Min Act: -0.1700

Data Index: 660419 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1007. Min Act: -0.1700

Data Index: 898389 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1323. Min Act: -0.1700

Data Index: 46102 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1007. Min Act: -0.1700

Data Index: 1192229 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1007. Min Act: -0.1700

Data Index: 15288 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1323. Min Act: -0.1700

Data Index: 109050 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1323. Min Act: -0.1700

Data Index: 1097316 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1323. Min Act: -0.1700

Data Index: 452186 (C4 (Web Text))

Max Activating Token Index: 300