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

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

Neuron 143 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.1737. Min Act: -0.1700

Data Index: 301307 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.1264. Min Act: -0.1700

Data Index: 1349302 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0949. Min Act: -0.1700

Data Index: 986585 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0949. Min Act: -0.1700

Data Index: 1296448 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0634. Min Act: -0.1700

Data Index: 368789 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0792. Min Act: -0.1700

Data Index: 20855 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0792. Min Act: -0.1700

Data Index: 1168557 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0792. Min Act: -0.1700

Data Index: 1054369 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0634. Min Act: -0.1700

Data Index: 1335237 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0476. Min Act: -0.1700

Data Index: 1205822 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0476. Min Act: -0.1700

Data Index: 649385 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0476. Min Act: -0.1700

Data Index: 154356 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0318. Min Act: -0.1700

Data Index: 737674 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0318. Min Act: -0.1700

Data Index: 1537865 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0318. Min Act: -0.1700

Data Index: 365633 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0318. Min Act: -0.1700

Data Index: 177109 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0160. Min Act: -0.1697

Data Index: 202015 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0160. Min Act: -0.1700

Data Index: 675487 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0318. Min Act: -0.1700

Data Index: 415651 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0318. Min Act: -0.1700

Data Index: 1183809 (C4 (Web Text))

Max Activating Token Index: 729