Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1121 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.8760. Min Act: -0.1700

Data Index: 807717 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.6260. Min Act: -0.1700

Data Index: 1122244 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.5947. Min Act: -0.1700

Data Index: 497424 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.6260. Min Act: -0.1700

Data Index: 919830 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.5010. Min Act: -0.1700

Data Index: 1279245 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.5322. Min Act: -0.1700

Data Index: 453816 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.5635. Min Act: -0.1700

Data Index: 821686 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.4697. Min Act: -0.1700

Data Index: 1292519 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.5010. Min Act: -0.1700

Data Index: 188186 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.4385. Min Act: -0.1700

Data Index: 132691 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.4072. Min Act: -0.1700

Data Index: 259612 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.4385. Min Act: -0.1700

Data Index: 819030 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.4072. Min Act: -0.1700

Data Index: 170882 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.4385. Min Act: -0.1700

Data Index: 602588 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.3447. Min Act: -0.1700

Data Index: 399802 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.3447. Min Act: -0.1700

Data Index: 623700 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.4072. Min Act: -0.1700

Data Index: 1332342 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.3447. Min Act: -0.1700

Data Index: 702966 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.3135. Min Act: -0.1700

Data Index: 1148504 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 5.8760. Min Range: -5.8760

Max Act: 5.3135. Min Act: -0.1700

Data Index: 185436 (C4 (Web Text))

Max Activating Token Index: 147