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

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

Neuron 1930 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: 3.2979. Min Range: -3.2979

Max Act: 3.2979. Min Act: -0.1700

Data Index: 1354746 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2350. Min Act: -0.1700

Data Index: 324389 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2350. Min Act: -0.1700

Data Index: 210738 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2350. Min Act: -0.1700

Data Index: 386561 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1878. Min Act: -0.1700

Data Index: 1180706 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1878. Min Act: -0.1700

Data Index: 758941 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1721. Min Act: -0.1700

Data Index: 810855 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1721. Min Act: -0.1700

Data Index: 160447 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2036. Min Act: -0.1700

Data Index: 112985 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1721. Min Act: -0.1700

Data Index: 843034 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1721. Min Act: -0.1700

Data Index: 213009 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1721. Min Act: -0.1700

Data Index: 1024538 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1721. Min Act: -0.1700

Data Index: 226269 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1563. Min Act: -0.1700

Data Index: 969202 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1721. Min Act: -0.1700

Data Index: 425964 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1406. Min Act: -0.1700

Data Index: 512327 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1563. Min Act: -0.1700

Data Index: 623433 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1248. Min Act: -0.1700

Data Index: 469554 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1248. Min Act: -0.1700

Data Index: 309304 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1406. Min Act: -0.1700

Data Index: 360132 (C4 (Web Text))

Max Activating Token Index: 283