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

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

Neuron 492 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1033. Min Range: -5.1033

Max Act: 5.1033. Min Act: -0.1700

Data Index: 320117 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 5.1033. Min Range: -5.1033

Max Act: 5.0408. Min Act: -0.1700

Data Index: 1342550 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.9783. Min Act: -0.1700

Data Index: 1087591 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.9471. Min Act: -0.1699

Data Index: 395596 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.9158. Min Act: -0.1700

Data Index: 289333 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.8846. Min Act: -0.1700

Data Index: 1330944 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.8846. Min Act: -0.1697

Data Index: 605688 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.8846. Min Act: -0.1700

Data Index: 829227 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.8221. Min Act: -0.1699

Data Index: 517845 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.8221. Min Act: -0.1700

Data Index: 1349874 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.8221. Min Act: -0.1700

Data Index: 882173 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.7908. Min Act: -0.1700

Data Index: 46891 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.7908. Min Act: -0.1700

Data Index: 925203 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.7596. Min Act: -0.1700

Data Index: 535155 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.7596. Min Act: -0.1700

Data Index: 772577 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.7596. Min Act: -0.1700

Data Index: 952969 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.6658. Min Act: -0.1699

Data Index: 999651 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.6346. Min Act: -0.1700

Data Index: 859123 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.6033. Min Act: -0.1700

Data Index: 1197013 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 5.1033. Min Range: -5.1033

Max Act: 4.6033. Min Act: -0.1700

Data Index: 64191 (C4 (Web Text))

Max Activating Token Index: 716