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

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

Neuron 977 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: 3.1016. Min Range: -3.1016

Max Act: 3.1016. Min Act: -0.1700

Data Index: 1454956 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0543. Min Act: -0.1700

Data Index: 1447816 (Python Code)

Max Activating Token Index: 273

Text #2

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0543. Min Act: -0.1700

Data Index: 1482088 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9278. Min Act: -0.1700

Data Index: 1596104 (Python Code)

Max Activating Token Index: 245

Text #4

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.8325. Min Act: -0.1700

Data Index: 360360 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.8325. Min Act: -0.1700

Data Index: 683877 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.8325. Min Act: -0.1700

Data Index: 615608 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.7848. Min Act: -0.1700

Data Index: 1591447 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.7529. Min Act: -0.1700

Data Index: 365282 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.7688. Min Act: -0.1700

Data Index: 652032 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.7369. Min Act: -0.1700

Data Index: 461228 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.7049. Min Act: -0.1700

Data Index: 654828 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.7049. Min Act: -0.1700

Data Index: 946626 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.7049. Min Act: -0.1700

Data Index: 1649434 (Python Code)

Max Activating Token Index: 277

Text #14

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.7209. Min Act: -0.1700

Data Index: 666383 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.6889. Min Act: -0.1700

Data Index: 1282664 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.6569. Min Act: -0.1700

Data Index: 370041 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.6569. Min Act: -0.1700

Data Index: 379377 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.6729. Min Act: -0.1700

Data Index: 786333 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.6569. Min Act: -0.1700

Data Index: 362369 (C4 (Web Text))

Max Activating Token Index: 159