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

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

Neuron 1705 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: 3.7455. Min Range: -3.7455

Max Act: 3.7455. Min Act: -0.1700

Data Index: 1117470 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6517. Min Act: -0.1700

Data Index: 798782 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6673. Min Act: -0.1700

Data Index: 1005508 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6517. Min Act: -0.1700

Data Index: 1267609 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6360. Min Act: -0.1700

Data Index: 335185 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5890. Min Act: -0.1700

Data Index: 938662 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6047. Min Act: -0.1700

Data Index: 374984 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5734. Min Act: -0.1700

Data Index: 397215 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5734. Min Act: -0.1700

Data Index: 852280 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5890. Min Act: -0.1700

Data Index: 532867 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5734. Min Act: -0.1700

Data Index: 3082 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4794. Min Act: -0.1700

Data Index: 341543 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5264. Min Act: -0.1700

Data Index: 45610 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5264. Min Act: -0.1700

Data Index: 491098 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5421. Min Act: -0.1700

Data Index: 1186921 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5421. Min Act: -0.1700

Data Index: 882585 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5264. Min Act: -0.1700

Data Index: 723432 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4951. Min Act: -0.1700

Data Index: 444276 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5107. Min Act: -0.1700

Data Index: 944115 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5264. Min Act: -0.1700

Data Index: 583787 (C4 (Web Text))

Max Activating Token Index: 607