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

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

Neuron 798 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: 3.7480. Min Range: -3.7480

Max Act: 3.7480. Min Act: -0.1700

Data Index: 1299318 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.5132. Min Act: -0.1700

Data Index: 564069 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.5132. Min Act: -0.1700

Data Index: 1069459 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4975. Min Act: -0.1700

Data Index: 1025523 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4819. Min Act: -0.1700

Data Index: 674128 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4975. Min Act: -0.1700

Data Index: 886225 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4975. Min Act: -0.1700

Data Index: 295298 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4505. Min Act: -0.1700

Data Index: 216043 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4662. Min Act: -0.1700

Data Index: 1266487 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4819. Min Act: -0.1700

Data Index: 1309973 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4819. Min Act: -0.1700

Data Index: 1252093 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4505. Min Act: -0.1700

Data Index: 1356607 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4348. Min Act: -0.1700

Data Index: 1223194 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4505. Min Act: -0.1700

Data Index: 1067988 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4348. Min Act: -0.1700

Data Index: 362363 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4505. Min Act: -0.1700

Data Index: 498887 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4192. Min Act: -0.1700

Data Index: 351747 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4192. Min Act: -0.1700

Data Index: 407411 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.3721. Min Act: -0.1700

Data Index: 46106 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 3.7480. Min Range: -3.7480

Max Act: 3.4192. Min Act: -0.1700

Data Index: 871890 (C4 (Web Text))

Max Activating Token Index: 753