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

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

Neuron 1258 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.6511. Min Act: -0.1700

Data Index: 1351251 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.6042. Min Act: -0.1700

Data Index: 637617 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.5102. Min Act: -0.1700

Data Index: 1057747 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4475. Min Act: -0.1700

Data Index: 678504 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4318. Min Act: -0.1700

Data Index: 454226 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4475. Min Act: -0.1700

Data Index: 1288936 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4632. Min Act: -0.1700

Data Index: 9147 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4318. Min Act: -0.1700

Data Index: 1323699 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4162. Min Act: -0.1700

Data Index: 588026 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4005. Min Act: -0.1700

Data Index: 726283 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4005. Min Act: -0.1700

Data Index: 1214861 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4005. Min Act: -0.1700

Data Index: 1001369 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3534. Min Act: -0.1700

Data Index: 860004 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3848. Min Act: -0.1700

Data Index: 1344221 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3534. Min Act: -0.1700

Data Index: 888168 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3377. Min Act: -0.1700

Data Index: 90832 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3377. Min Act: -0.1700

Data Index: 812890 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3534. Min Act: -0.1700

Data Index: 905122 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3377. Min Act: -0.1700

Data Index: 428195 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3220. Min Act: -0.1700

Data Index: 182885 (C4 (Web Text))

Max Activating Token Index: 640