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

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

Neuron 1072 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.2283. Min Act: -0.1700

Data Index: 984685 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.1496. Min Act: -0.1700

Data Index: 705229 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.1654. Min Act: -0.1700

Data Index: 493279 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.1496. Min Act: -0.1700

Data Index: 76406 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.1339. Min Act: -0.1700

Data Index: 73712 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.1023. Min Act: -0.1700

Data Index: 1219623 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.1023. Min Act: -0.1700

Data Index: 1215927 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.1023. Min Act: -0.1700

Data Index: 494451 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.1023. Min Act: -0.1700

Data Index: 880610 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0866. Min Act: -0.1700

Data Index: 299910 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0550. Min Act: -0.1700

Data Index: 684090 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0708. Min Act: -0.1700

Data Index: 1055480 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0550. Min Act: -0.1700

Data Index: 138536 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0550. Min Act: -0.1700

Data Index: 1092346 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0550. Min Act: -0.1700

Data Index: 915947 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0392. Min Act: -0.1700

Data Index: 1086105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0234. Min Act: -0.1700

Data Index: 98246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0392. Min Act: -0.1700

Data Index: 1195964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0076. Min Act: -0.1700

Data Index: 240062 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0076. Min Act: -0.1700

Data Index: 1026540 (C4 (Web Text))

Max Activating Token Index: 1023