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

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

Neuron 1268 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2785. Min Range: -4.2785

Max Act: 4.2785. Min Act: -0.1700

Data Index: 817442 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 4.2785. Min Range: -4.2785

Max Act: 4.1848. Min Act: -0.1700

Data Index: 635617 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 4.2785. Min Range: -4.2785

Max Act: 4.1535. Min Act: -0.1700

Data Index: 427846 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 4.2785. Min Range: -4.2785

Max Act: 4.0910. Min Act: -0.1700

Data Index: 572483 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 4.2785. Min Range: -4.2785

Max Act: 4.0597. Min Act: -0.1700

Data Index: 792203 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 4.2785. Min Range: -4.2785

Max Act: 4.1223. Min Act: -0.1700

Data Index: 965846 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 4.2785. Min Range: -4.2785

Max Act: 4.0597. Min Act: -0.1700

Data Index: 728269 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.9972. Min Act: -0.1700

Data Index: 1023807 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.9659. Min Act: -0.1700

Data Index: 1132429 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.9659. Min Act: -0.1700

Data Index: 509275 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.8721. Min Act: -0.1700

Data Index: 385897 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.9034. Min Act: -0.1700

Data Index: 1016591 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.8408. Min Act: -0.1700

Data Index: 808774 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.8408. Min Act: -0.1700

Data Index: 301470 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.8721. Min Act: -0.1700

Data Index: 536952 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.8721. Min Act: -0.1700

Data Index: 40845 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.8096. Min Act: -0.1700

Data Index: 93516 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.8096. Min Act: -0.1700

Data Index: 650461 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.8408. Min Act: -0.1700

Data Index: 621813 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 4.2785. Min Range: -4.2785

Max Act: 3.8096. Min Act: -0.1700

Data Index: 176645 (C4 (Web Text))

Max Activating Token Index: 192