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

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

Neuron 162 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: 3.1049. Min Range: -3.1049

Max Act: 3.1049. Min Act: -0.1700

Data Index: 5970 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0891. Min Act: -0.1700

Data Index: 918910 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0733. Min Act: -0.1700

Data Index: 942020 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0733. Min Act: -0.1700

Data Index: 957240 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0733. Min Act: -0.1700

Data Index: 976148 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0575. Min Act: -0.1700

Data Index: 914642 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0418. Min Act: -0.1700

Data Index: 479693 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0418. Min Act: -0.1700

Data Index: 518302 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0418. Min Act: -0.1700

Data Index: 267340 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0418. Min Act: -0.1700

Data Index: 448918 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0418. Min Act: -0.1700

Data Index: 342015 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0260. Min Act: -0.1700

Data Index: 932699 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0260. Min Act: -0.1700

Data Index: 1229131 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0260. Min Act: -0.1700

Data Index: 1126893 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0102. Min Act: -0.1700

Data Index: 406712 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0102. Min Act: -0.1700

Data Index: 1009485 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 3.1049. Min Range: -3.1049

Max Act: 3.0102. Min Act: -0.1700

Data Index: 777720 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 3.1049. Min Range: -3.1049

Max Act: 2.9943. Min Act: -0.1700

Data Index: 1018200 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 3.1049. Min Range: -3.1049

Max Act: 2.9943. Min Act: -0.1700

Data Index: 1250131 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 3.1049. Min Range: -3.1049

Max Act: 2.9943. Min Act: -0.1700

Data Index: 643240 (C4 (Web Text))

Max Activating Token Index: 947