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

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

Neuron 590 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: 3.2630. Min Range: -3.2630

Max Act: 3.2630. Min Act: -0.1700

Data Index: 1563796 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.2002. Min Act: -0.1700

Data Index: 27413 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1844. Min Act: -0.1700

Data Index: 440473 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1844. Min Act: -0.1700

Data Index: 49142 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1372. Min Act: -0.1700

Data Index: 572285 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1529. Min Act: -0.1700

Data Index: 1630143 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1372. Min Act: -0.1700

Data Index: 853528 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1529. Min Act: -0.1700

Data Index: 1336152 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1372. Min Act: -0.1700

Data Index: 1230696 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1214. Min Act: -0.1700

Data Index: 919022 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1214. Min Act: -0.1700

Data Index: 1344850 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1529. Min Act: -0.1700

Data Index: 1503373 (Python Code)

Max Activating Token Index: 846

Text #12

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1214. Min Act: -0.1700

Data Index: 1630702 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1214. Min Act: -0.1700

Data Index: 1279772 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1214. Min Act: -0.1700

Data Index: 46553 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1214. Min Act: -0.1700

Data Index: 1326345 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1214. Min Act: -0.1700

Data Index: 802586 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1214. Min Act: -0.1700

Data Index: 1026247 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1057. Min Act: -0.1700

Data Index: 1340772 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.0899. Min Act: -0.1700

Data Index: 794568 (C4 (Web Text))

Max Activating Token Index: 926