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

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

Neuron 128 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5598. Min Range: -7.5598

Max Act: 7.5598. Min Act: -0.1700

Data Index: 1259521 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 7.5598. Min Range: -7.5598

Max Act: 7.2473. Min Act: -0.1700

Data Index: 254688 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 7.5598. Min Range: -7.5598

Max Act: 7.1848. Min Act: -0.1700

Data Index: 382147 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 7.5598. Min Range: -7.5598

Max Act: 7.1223. Min Act: -0.1700

Data Index: 956650 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 7.5598. Min Range: -7.5598

Max Act: 7.1223. Min Act: -0.1700

Data Index: 302537 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 7.5598. Min Range: -7.5598

Max Act: 7.1223. Min Act: -0.1700

Data Index: 1173462 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 7.5598. Min Range: -7.5598

Max Act: 7.1223. Min Act: -0.1700

Data Index: 419621 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.9973. Min Act: -0.1700

Data Index: 125049 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 7.5598. Min Range: -7.5598

Max Act: 7.0598. Min Act: -0.1700

Data Index: 1356591 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.9973. Min Act: -0.1700

Data Index: 1300853 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.9973. Min Act: -0.1700

Data Index: 567471 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 7.5598. Min Range: -7.5598

Max Act: 7.0598. Min Act: -0.1700

Data Index: 354438 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.9348. Min Act: -0.1700

Data Index: 665688 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.9348. Min Act: -0.1700

Data Index: 695018 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.9348. Min Act: -0.1700

Data Index: 222863 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.9973. Min Act: -0.1700

Data Index: 203113 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.9973. Min Act: -0.1700

Data Index: 1109992 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.8411. Min Act: -0.1700

Data Index: 1080724 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.9348. Min Act: -0.1700

Data Index: 915614 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 7.5598. Min Range: -7.5598

Max Act: 6.8411. Min Act: -0.1700

Data Index: 342590 (C4 (Web Text))

Max Activating Token Index: 935