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

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

Neuron 2021 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: 3.2199. Min Range: -3.2199

Max Act: 3.2199. Min Act: -0.1700

Data Index: 1404509 (Python Code)

Max Activating Token Index: 127

Text #1

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.2199. Min Act: -0.1700

Data Index: 1447118 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.1254. Min Act: -0.1700

Data Index: 1503297 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0939. Min Act: -0.1700

Data Index: 1503193 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0781. Min Act: -0.1700

Data Index: 1575407 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0939. Min Act: -0.1700

Data Index: 1387424 (Python Code)

Max Activating Token Index: 903

Text #6

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0624. Min Act: -0.1700

Data Index: 1426832 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0308. Min Act: -0.1700

Data Index: 1642207 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0308. Min Act: -0.1700

Data Index: 1575271 (Python Code)

Max Activating Token Index: 388

Text #9

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0466. Min Act: -0.1700

Data Index: 1497817 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0466. Min Act: -0.1700

Data Index: 1488637 (Python Code)

Max Activating Token Index: 441

Text #11

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0308. Min Act: -0.1700

Data Index: 1559884 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0466. Min Act: -0.1700

Data Index: 320062 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0150. Min Act: -0.1700

Data Index: 1533254 (Python Code)

Max Activating Token Index: 697

Text #14

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0466. Min Act: -0.1700

Data Index: 1534111 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 3.2199. Min Range: -3.2199

Max Act: 2.9992. Min Act: -0.1700

Data Index: 1399576 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0150. Min Act: -0.1700

Data Index: 1584702 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0150. Min Act: -0.1700

Data Index: 1614959 (Python Code)

Max Activating Token Index: 936

Text #18

Max Range: 3.2199. Min Range: -3.2199

Max Act: 3.0308. Min Act: -0.1700

Data Index: 1531952 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 3.2199. Min Range: -3.2199

Max Act: 2.9992. Min Act: -0.1700

Data Index: 1505737 (Python Code)

Max Activating Token Index: 837