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

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

Neuron 261 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.3406. Min Act: -0.1700

Data Index: 900756 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.2935. Min Act: -0.1700

Data Index: 431015 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.2149. Min Act: -0.1700

Data Index: 269685 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.2307. Min Act: -0.1700

Data Index: 1306919 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1992. Min Act: -0.1700

Data Index: 82282 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1992. Min Act: -0.1700

Data Index: 665796 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1992. Min Act: -0.1700

Data Index: 389413 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1992. Min Act: -0.1700

Data Index: 778783 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1835. Min Act: -0.1700

Data Index: 508047 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1520. Min Act: -0.1700

Data Index: 289365 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1362. Min Act: -0.1700

Data Index: 124974 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1677. Min Act: -0.1700

Data Index: 199668 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1677. Min Act: -0.1700

Data Index: 199336 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1205. Min Act: -0.1700

Data Index: 1054767 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1520. Min Act: -0.1700

Data Index: 604762 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1362. Min Act: -0.1700

Data Index: 1091346 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1205. Min Act: -0.1700

Data Index: 1024824 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1362. Min Act: -0.1700

Data Index: 982870 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1520. Min Act: -0.1700

Data Index: 414434 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 3.3406. Min Range: -3.3406

Max Act: 3.1047. Min Act: -0.1700

Data Index: 859305 (C4 (Web Text))

Max Activating Token Index: 822