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

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

Neuron 1510 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: 7.0694. Min Range: -7.0694

Max Act: 7.0694. Min Act: -0.1700

Data Index: 7117 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.6319. Min Act: -0.1700

Data Index: 205333 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.6007. Min Act: -0.1700

Data Index: 934952 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.6007. Min Act: -0.1700

Data Index: 106614 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.5069. Min Act: -0.1700

Data Index: 1112798 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.3819. Min Act: -0.1700

Data Index: 567036 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.4757. Min Act: -0.1700

Data Index: 1247243 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.3507. Min Act: -0.1700

Data Index: 1294922 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.3819. Min Act: -0.1700

Data Index: 635468 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.3507. Min Act: -0.1699

Data Index: 823695 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.2882. Min Act: -0.1700

Data Index: 441847 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.3507. Min Act: -0.1700

Data Index: 1138724 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.2257. Min Act: -0.1699

Data Index: 537082 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.3507. Min Act: -0.1700

Data Index: 711870 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.2569. Min Act: -0.1700

Data Index: 1291564 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.2882. Min Act: -0.1700

Data Index: 633561 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.2569. Min Act: -0.1700

Data Index: 506287 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.2569. Min Act: -0.1700

Data Index: 238014 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.1944. Min Act: -0.1699

Data Index: 591029 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 7.0694. Min Range: -7.0694

Max Act: 6.2569. Min Act: -0.1699

Data Index: 495956 (C4 (Web Text))

Max Activating Token Index: 81