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

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

Neuron 567 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: 7.6616. Min Range: -7.6616

Max Act: 7.5991. Min Act: -0.1700

Data Index: 1252192 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.6616. Min Act: -0.1700

Data Index: 72388 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.3491. Min Act: -0.1700

Data Index: 1099625 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.4116. Min Act: -0.1700

Data Index: 760279 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.2866. Min Act: -0.1700

Data Index: 576824 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.3491. Min Act: -0.1700

Data Index: 1296369 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.1616. Min Act: -0.1700

Data Index: 119709 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.1616. Min Act: -0.1700

Data Index: 568725 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.0991. Min Act: -0.1700

Data Index: 512786 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.0991. Min Act: -0.1700

Data Index: 728214 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.3491. Min Act: -0.1700

Data Index: 59308 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.2241. Min Act: -0.1700

Data Index: 20438 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.1616. Min Act: -0.1700

Data Index: 719873 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.1616. Min Act: -0.1700

Data Index: 68210 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 7.6616. Min Range: -7.6616

Max Act: 6.9741. Min Act: -0.1700

Data Index: 1026107 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.0366. Min Act: -0.1700

Data Index: 1072633 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.0366. Min Act: -0.1700

Data Index: 1125306 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.0366. Min Act: -0.1700

Data Index: 250527 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 7.6616. Min Range: -7.6616

Max Act: 7.0991. Min Act: -0.1700

Data Index: 699506 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 7.6616. Min Range: -7.6616

Max Act: 6.9741. Min Act: -0.1700

Data Index: 611787 (C4 (Web Text))

Max Activating Token Index: 312