Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 906 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.3879. Min Act: -0.1700

Data Index: 1291006 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.3722. Min Act: -0.1700

Data Index: 99316 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.3251. Min Act: -0.1700

Data Index: 442867 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.3094. Min Act: -0.1700

Data Index: 593676 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.2937. Min Act: -0.1700

Data Index: 1065691 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.2623. Min Act: -0.1700

Data Index: 1106420 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.2465. Min Act: -0.1700

Data Index: 6583 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.2151. Min Act: -0.1700

Data Index: 1228242 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.1994. Min Act: -0.1700

Data Index: 589295 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.2151. Min Act: -0.1700

Data Index: 1265562 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.2151. Min Act: -0.1700

Data Index: 1046301 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.1994. Min Act: -0.1700

Data Index: 1223717 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.1994. Min Act: -0.1700

Data Index: 612913 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.1836. Min Act: -0.1700

Data Index: 425783 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.2151. Min Act: -0.1700

Data Index: 141227 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.1836. Min Act: -0.1700

Data Index: 503565 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.1836. Min Act: -0.1700

Data Index: 11107 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.1836. Min Act: -0.1700

Data Index: 817725 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.1836. Min Act: -0.1700

Data Index: 183433 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.1836. Min Act: -0.1700

Data Index: 513425 (C4 (Web Text))

Max Activating Token Index: 221