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

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

Neuron 1259 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.6165. Min Act: -0.1700

Data Index: 1000329 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.6165. Min Act: -0.1700

Data Index: 1152121 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.6008. Min Act: -0.1700

Data Index: 1111067 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5852. Min Act: -0.1700

Data Index: 470192 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.6008. Min Act: -0.1700

Data Index: 213489 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.6165. Min Act: -0.1700

Data Index: 1136280 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5852. Min Act: -0.1700

Data Index: 1229 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5852. Min Act: -0.1700

Data Index: 65985 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5852. Min Act: -0.1700

Data Index: 548292 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5382. Min Act: -0.1700

Data Index: 801 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5382. Min Act: -0.1700

Data Index: 164258 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5382. Min Act: -0.1700

Data Index: 1141620 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5695. Min Act: -0.1700

Data Index: 744710 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5539. Min Act: -0.1700

Data Index: 100222 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5852. Min Act: -0.1700

Data Index: 746003 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5539. Min Act: -0.1700

Data Index: 529391 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5695. Min Act: -0.1700

Data Index: 55606 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5695. Min Act: -0.1700

Data Index: 9496 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5695. Min Act: -0.1700

Data Index: 1073937 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 3.6165. Min Range: -3.6165

Max Act: 3.5382. Min Act: -0.1700

Data Index: 670905 (C4 (Web Text))

Max Activating Token Index: 658