Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 371 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.9509. Min Act: -0.1700

Data Index: 293874 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.8258. Min Act: -0.1700

Data Index: 855269 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.7476. Min Act: -0.1700

Data Index: 114257 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.7006. Min Act: -0.1700

Data Index: 1327680 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6693. Min Act: -0.1700

Data Index: 861437 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.7006. Min Act: -0.1700

Data Index: 1181492 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6067. Min Act: -0.1700

Data Index: 706194 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6693. Min Act: -0.1700

Data Index: 556447 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6537. Min Act: -0.1700

Data Index: 259371 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6380. Min Act: -0.1700

Data Index: 591556 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.7319. Min Act: -0.1700

Data Index: 112466 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6224. Min Act: -0.1700

Data Index: 461004 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6380. Min Act: -0.1700

Data Index: 1255244 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6380. Min Act: -0.1700

Data Index: 955562 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6380. Min Act: -0.1700

Data Index: 754371 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6380. Min Act: -0.1700

Data Index: 803902 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.5911. Min Act: -0.1700

Data Index: 1196943 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6224. Min Act: -0.1700

Data Index: 1244006 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6537. Min Act: -0.1700

Data Index: 5719 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.9509. Min Range: -3.9509

Max Act: 3.6537. Min Act: -0.1700

Data Index: 1060917 (C4 (Web Text))

Max Activating Token Index: 422