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

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

Neuron 1822 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.3459. Min Act: -0.1700

Data Index: 1159216 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2831. Min Act: -0.1700

Data Index: 1195576 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2831. Min Act: -0.1700

Data Index: 1340487 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2360. Min Act: -0.1700

Data Index: 669712 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2202. Min Act: -0.1700

Data Index: 1142455 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2360. Min Act: -0.1700

Data Index: 1029545 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2045. Min Act: -0.1700

Data Index: 23509 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1888. Min Act: -0.1700

Data Index: 202868 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1888. Min Act: -0.1700

Data Index: 250340 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1730. Min Act: -0.1700

Data Index: 413212 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1888. Min Act: -0.1700

Data Index: 612430 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1730. Min Act: -0.1700

Data Index: 303885 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1888. Min Act: -0.1700

Data Index: 1073539 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1730. Min Act: -0.1700

Data Index: 1270894 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1730. Min Act: -0.1700

Data Index: 552145 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1573. Min Act: -0.1700

Data Index: 399466 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1573. Min Act: -0.1700

Data Index: 317345 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1573. Min Act: -0.1700

Data Index: 345651 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1415. Min Act: -0.1700

Data Index: 573027 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1415. Min Act: -0.1700

Data Index: 597723 (C4 (Web Text))

Max Activating Token Index: 845