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

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

Neuron 323 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: 5.3995. Min Range: -5.3995

Max Act: 5.3683. Min Act: -0.1700

Data Index: 762379 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.3995. Min Act: -0.1700

Data Index: 844296 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.2745. Min Act: -0.1700

Data Index: 504472 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.2745. Min Act: -0.1700

Data Index: 556786 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.2120. Min Act: -0.1700

Data Index: 676264 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.1495. Min Act: -0.1700

Data Index: 1138906 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.1183. Min Act: -0.1700

Data Index: 499063 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.0870. Min Act: -0.1700

Data Index: 1043146 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.0870. Min Act: -0.1700

Data Index: 259473 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.0558. Min Act: -0.1700

Data Index: 757415 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.0558. Min Act: -0.1700

Data Index: 14505 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.0870. Min Act: -0.1700

Data Index: 210245 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.0245. Min Act: -0.1700

Data Index: 947575 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.0558. Min Act: -0.1700

Data Index: 1270533 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.0245. Min Act: -0.1700

Data Index: 1155086 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 5.3995. Min Range: -5.3995

Max Act: 4.9933. Min Act: -0.1700

Data Index: 1340187 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 5.3995. Min Range: -5.3995

Max Act: 4.9933. Min Act: -0.1700

Data Index: 1177736 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 5.3995. Min Range: -5.3995

Max Act: 5.0245. Min Act: -0.1699

Data Index: 944483 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 5.3995. Min Range: -5.3995

Max Act: 4.9620. Min Act: -0.1700

Data Index: 1054573 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 5.3995. Min Range: -5.3995

Max Act: 4.9620. Min Act: -0.1700

Data Index: 151315 (C4 (Web Text))

Max Activating Token Index: 270