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

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

Neuron 909 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: 5.6081. Min Range: -5.6081

Max Act: 5.5769. Min Act: -0.1700

Data Index: 887561 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.6081. Min Act: -0.1700

Data Index: 370150 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.6081. Min Act: -0.1700

Data Index: 177690 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.5456. Min Act: -0.1700

Data Index: 887693 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.5456. Min Act: -0.1700

Data Index: 1110487 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.5769. Min Act: -0.1700

Data Index: 1109774 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.5456. Min Act: -0.1700

Data Index: 216286 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.4519. Min Act: -0.1700

Data Index: 781778 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.4519. Min Act: -0.1700

Data Index: 365089 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.3894. Min Act: -0.1700

Data Index: 1293460 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.4206. Min Act: -0.1700

Data Index: 1266879 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.4519. Min Act: -0.1700

Data Index: 455790 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.5144. Min Act: -0.1700

Data Index: 316163 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.4519. Min Act: -0.1700

Data Index: 41476 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.4831. Min Act: -0.1700

Data Index: 837955 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.4831. Min Act: -0.1700

Data Index: 612617 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.3894. Min Act: -0.1700

Data Index: 254641 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.3581. Min Act: -0.1700

Data Index: 367648 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.4519. Min Act: -0.1700

Data Index: 537864 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.4206. Min Act: -0.1700

Data Index: 179623 (C4 (Web Text))

Max Activating Token Index: 421