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

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

Neuron 765 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: 3.3231. Min Range: -3.3231

Max Act: 3.3231. Min Act: -0.1700

Data Index: 653109 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.2288. Min Act: -0.1700

Data Index: 1004843 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.2288. Min Act: -0.1700

Data Index: 788097 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1973. Min Act: -0.1700

Data Index: 46698 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1973. Min Act: -0.1700

Data Index: 162356 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1973. Min Act: -0.1700

Data Index: 792403 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1973. Min Act: -0.1700

Data Index: 1085910 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1659. Min Act: -0.1700

Data Index: 1096597 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1659. Min Act: -0.1700

Data Index: 454869 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1344. Min Act: -0.1700

Data Index: 221630 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1028. Min Act: -0.1700

Data Index: 1257885 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1028. Min Act: -0.1700

Data Index: 1327041 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0555. Min Act: -0.1700

Data Index: 1089583 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1028. Min Act: -0.1700

Data Index: 120021 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1344. Min Act: -0.1700

Data Index: 659447 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0555. Min Act: -0.1700

Data Index: 394630 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0713. Min Act: -0.1700

Data Index: 388795 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1028. Min Act: -0.1700

Data Index: 252184 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0555. Min Act: -0.1700

Data Index: 324136 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0713. Min Act: -0.1700

Data Index: 791742 (C4 (Web Text))

Max Activating Token Index: 575