Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1722 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.6495. Min Act: -0.1700

Data Index: 794929 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5573. Min Act: -0.1700

Data Index: 1027512 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5463. Min Act: -0.1700

Data Index: 680205 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4996. Min Act: -0.1700

Data Index: 431519 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4814. Min Act: -0.1700

Data Index: 955437 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4601. Min Act: -0.1699

Data Index: 927956 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4478. Min Act: -0.1700

Data Index: 478796 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4562. Min Act: -0.1693

Data Index: 969880 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4564. Min Act: -0.1700

Data Index: 265173 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4362. Min Act: -0.1700

Data Index: 467982 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4263. Min Act: -0.1698

Data Index: 661893 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4271. Min Act: -0.1698

Data Index: 852798 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.3968. Min Act: -0.1700

Data Index: 484783 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4141. Min Act: -0.1700

Data Index: 748957 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4071. Min Act: -0.1700

Data Index: 566913 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.3919. Min Act: -0.1700

Data Index: 391070 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.3858. Min Act: -0.1700

Data Index: 941209 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4068. Min Act: -0.1700

Data Index: 437916 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.3912. Min Act: -0.1700

Data Index: 1143617 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.3889. Min Act: -0.1700

Data Index: 1189710 (C4 (Web Text))

Max Activating Token Index: 942