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

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

Neuron 1790 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: 3.6066. Min Range: -3.6066

Max Act: 3.6066. Min Act: -0.1700

Data Index: 14980 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.5440. Min Act: -0.1700

Data Index: 236673 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.5127. Min Act: -0.1700

Data Index: 604709 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.5127. Min Act: -0.1700

Data Index: 1137880 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4813. Min Act: -0.1700

Data Index: 1279918 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4813. Min Act: -0.1700

Data Index: 1116924 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4500. Min Act: -0.1700

Data Index: 260352 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4500. Min Act: -0.1700

Data Index: 416987 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4186. Min Act: -0.1700

Data Index: 760086 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4186. Min Act: -0.1700

Data Index: 472256 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4186. Min Act: -0.1700

Data Index: 388407 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4500. Min Act: -0.1700

Data Index: 873307 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4500. Min Act: -0.1700

Data Index: 176291 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4500. Min Act: -0.1700

Data Index: 291607 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4186. Min Act: -0.1700

Data Index: 797951 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4500. Min Act: -0.1700

Data Index: 1068650 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.3873. Min Act: -0.1700

Data Index: 518069 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4186. Min Act: -0.1700

Data Index: 515165 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4186. Min Act: -0.1700

Data Index: 159871 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 3.6066. Min Range: -3.6066

Max Act: 3.4186. Min Act: -0.1700

Data Index: 119665 (C4 (Web Text))

Max Activating Token Index: 485