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

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

Neuron 620 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: 3.1348. Min Range: -3.1348

Max Act: 3.1348. Min Act: -0.1700

Data Index: 780806 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.1190. Min Act: -0.1700

Data Index: 1149531 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0875. Min Act: -0.1700

Data Index: 331285 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0875. Min Act: -0.1700

Data Index: 569329 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0402. Min Act: -0.1700

Data Index: 991571 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0402. Min Act: -0.1700

Data Index: 156466 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.9928. Min Act: -0.1700

Data Index: 90999 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0086. Min Act: -0.1700

Data Index: 1041378 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0402. Min Act: -0.1700

Data Index: 461495 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0559. Min Act: -0.1700

Data Index: 213403 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0402. Min Act: -0.1700

Data Index: 615784 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0086. Min Act: -0.1700

Data Index: 304808 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0086. Min Act: -0.1700

Data Index: 155189 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0244. Min Act: -0.1700

Data Index: 440057 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0086. Min Act: -0.1700

Data Index: 1233956 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0244. Min Act: -0.1700

Data Index: 979901 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.9928. Min Act: -0.1700

Data Index: 1272802 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0086. Min Act: -0.1700

Data Index: 1342697 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.0086. Min Act: -0.1700

Data Index: 608207 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.9453. Min Act: -0.1700

Data Index: 1057209 (C4 (Web Text))

Max Activating Token Index: 529