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

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

Neuron 1663 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: 3.9094. Min Range: -3.9094

Max Act: 3.9094. Min Act: -0.1700

Data Index: 1125322 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.8469. Min Act: -0.1700

Data Index: 1151968 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.8156. Min Act: -0.1700

Data Index: 1234584 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.7530. Min Act: -0.1700

Data Index: 726269 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.6904. Min Act: -0.1700

Data Index: 1118074 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.7217. Min Act: -0.1700

Data Index: 356558 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.6904. Min Act: -0.1700

Data Index: 127341 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.6591. Min Act: -0.1700

Data Index: 1112473 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.6591. Min Act: -0.1700

Data Index: 644991 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.6278. Min Act: -0.1700

Data Index: 1074457 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.6278. Min Act: -0.1700

Data Index: 267320 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.6278. Min Act: -0.1700

Data Index: 520203 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.6591. Min Act: -0.1700

Data Index: 217722 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.6278. Min Act: -0.1700

Data Index: 430527 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.5965. Min Act: -0.1700

Data Index: 946116 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.5965. Min Act: -0.1700

Data Index: 425722 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.5809. Min Act: -0.1700

Data Index: 200598 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.5809. Min Act: -0.1700

Data Index: 1535565 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.5809. Min Act: -0.1700

Data Index: 576331 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.5809. Min Act: -0.1700

Data Index: 77792 (C4 (Web Text))

Max Activating Token Index: 894