Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 2013 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.8701. Min Act: -0.1699

Data Index: 1621834 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.8701. Min Act: -0.1699

Data Index: 1649826 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.8168. Min Act: -0.1700

Data Index: 1522650 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.8088. Min Act: -0.1700

Data Index: 1471489 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.7948. Min Act: -0.1700

Data Index: 1440319 (Python Code)

Max Activating Token Index: 245

Text #5

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.8032. Min Act: -0.1700

Data Index: 1536382 (Python Code)

Max Activating Token Index: 350

Text #6

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.7712. Min Act: -0.1700

Data Index: 1418200 (Python Code)

Max Activating Token Index: 345

Text #7

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.7448. Min Act: -0.1699

Data Index: 1468527 (Python Code)

Max Activating Token Index: 182

Text #8

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.7167. Min Act: -0.1700

Data Index: 1367405 (Python Code)

Max Activating Token Index: 928

Text #9

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.7095. Min Act: -0.1700

Data Index: 1608724 (Python Code)

Max Activating Token Index: 641

Text #10

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.7182. Min Act: -0.1700

Data Index: 1580601 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.7117. Min Act: -0.1700

Data Index: 731895 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.6965. Min Act: -0.1700

Data Index: 1360378 (Python Code)

Max Activating Token Index: 139

Text #13

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.7073. Min Act: -0.1700

Data Index: 1547311 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.7025. Min Act: -0.1700

Data Index: 1443221 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.6877. Min Act: -0.1700

Data Index: 1503538 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.6945. Min Act: -0.1700

Data Index: 1629859 (Python Code)

Max Activating Token Index: 823

Text #17

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.6900. Min Act: -0.1700

Data Index: 870778 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.6693. Min Act: -0.1700

Data Index: 1410760 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 3.8701. Min Range: -3.8701

Max Act: 3.6864. Min Act: -0.1700

Data Index: 1497456 (Python Code)

Max Activating Token Index: 70