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

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

Neuron 820 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: 3.4085. Min Range: -3.4085

Max Act: 3.3928. Min Act: -0.1700

Data Index: 1055087 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3928. Min Act: -0.1700

Data Index: 1217720 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.4085. Min Act: -0.1700

Data Index: 592139 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3771. Min Act: -0.1700

Data Index: 1206692 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3771. Min Act: -0.1700

Data Index: 277183 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3614. Min Act: -0.1700

Data Index: 1111192 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3614. Min Act: -0.1700

Data Index: 1075735 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3614. Min Act: -0.1700

Data Index: 1347976 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3300. Min Act: -0.1700

Data Index: 546433 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2986. Min Act: -0.1700

Data Index: 828351 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3143. Min Act: -0.1700

Data Index: 568832 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2986. Min Act: -0.1700

Data Index: 1335300 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2986. Min Act: -0.1700

Data Index: 804588 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3457. Min Act: -0.1700

Data Index: 963429 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3143. Min Act: -0.1700

Data Index: 448168 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2829. Min Act: -0.1700

Data Index: 818785 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2986. Min Act: -0.1700

Data Index: 795088 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2672. Min Act: -0.1700

Data Index: 235695 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2986. Min Act: -0.1700

Data Index: 982167 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2829. Min Act: -0.1700

Data Index: 495742 (C4 (Web Text))

Max Activating Token Index: 369