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

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

Neuron 24 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.4343. Min Act: -0.1700

Data Index: 1150034 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.3872. Min Act: -0.1700

Data Index: 539287 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.3245. Min Act: -0.1700

Data Index: 496307 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2616. Min Act: -0.1700

Data Index: 279336 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2616. Min Act: -0.1700

Data Index: 508405 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2616. Min Act: -0.1700

Data Index: 367225 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2459. Min Act: -0.1700

Data Index: 1289440 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2616. Min Act: -0.1700

Data Index: 524719 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2302. Min Act: -0.1700

Data Index: 403564 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2459. Min Act: -0.1700

Data Index: 222867 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2459. Min Act: -0.1700

Data Index: 584370 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2459. Min Act: -0.1700

Data Index: 392830 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2459. Min Act: -0.1700

Data Index: 300878 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2459. Min Act: -0.1700

Data Index: 170103 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2302. Min Act: -0.1700

Data Index: 1170991 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2302. Min Act: -0.1700

Data Index: 72330 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2302. Min Act: -0.1700

Data Index: 146543 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2145. Min Act: -0.1700

Data Index: 504829 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2302. Min Act: -0.1700

Data Index: 348583 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.4343. Min Range: -3.4343

Max Act: 3.2145. Min Act: -0.1700

Data Index: 111651 (C4 (Web Text))

Max Activating Token Index: 197