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

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

Neuron 1451 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: 5.1486. Min Range: -5.1486

Max Act: 5.1486. Min Act: -0.1700

Data Index: 571365 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 5.1486. Min Range: -5.1486

Max Act: 5.1174. Min Act: -0.1700

Data Index: 104253 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 5.1486. Min Range: -5.1486

Max Act: 5.1486. Min Act: -0.1700

Data Index: 1238513 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 5.1486. Min Range: -5.1486

Max Act: 5.0549. Min Act: -0.1700

Data Index: 136044 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.9924. Min Act: -0.1700

Data Index: 422342 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.9298. Min Act: -0.1700

Data Index: 573407 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.9611. Min Act: -0.1700

Data Index: 504909 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.9298. Min Act: -0.1700

Data Index: 184859 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.9298. Min Act: -0.1700

Data Index: 544674 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.9298. Min Act: -0.1700

Data Index: 1346251 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.9298. Min Act: -0.1700

Data Index: 438118 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.9611. Min Act: -0.1700

Data Index: 153496 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.8986. Min Act: -0.1700

Data Index: 544475 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.9611. Min Act: -0.1700

Data Index: 676668 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.8673. Min Act: -0.1700

Data Index: 1159418 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.8986. Min Act: -0.1700

Data Index: 543318 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.8673. Min Act: -0.1700

Data Index: 773181 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.8673. Min Act: -0.1700

Data Index: 248644 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.8986. Min Act: -0.1700

Data Index: 335385 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 5.1486. Min Range: -5.1486

Max Act: 4.7423. Min Act: -0.1700

Data Index: 4243 (C4 (Web Text))

Max Activating Token Index: 252