Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 986 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.4666. Min Act: -0.1700

Data Index: 204677 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.2478. Min Act: -0.1700

Data Index: 1090032 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.2010. Min Act: -0.1700

Data Index: 588880 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.1228. Min Act: -0.1700

Data Index: 1056993 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.0916. Min Act: -0.1700

Data Index: 1069882 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.9666. Min Act: -0.1700

Data Index: 440983 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.9197. Min Act: -0.1700

Data Index: 105713 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.9041. Min Act: -0.1700

Data Index: 1103166 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.7947. Min Act: -0.1700

Data Index: 823207 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.8416. Min Act: -0.1700

Data Index: 1323848 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.7322. Min Act: -0.1700

Data Index: 113609 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.7791. Min Act: -0.1700

Data Index: 1133677 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.8260. Min Act: -0.1700

Data Index: 1354881 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.8260. Min Act: -0.1700

Data Index: 284688 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.7791. Min Act: -0.1700

Data Index: 816522 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.8416. Min Act: -0.1700

Data Index: 298520 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.7791. Min Act: -0.1700

Data Index: 604878 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.8103. Min Act: -0.1700

Data Index: 607760 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.7947. Min Act: -0.1700

Data Index: 89898 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 5.4666. Min Range: -5.4666

Max Act: 4.7478. Min Act: -0.1700

Data Index: 163781 (C4 (Web Text))

Max Activating Token Index: 468