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

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

Neuron 702 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: 9.0498. Min Range: -9.0498

Max Act: 9.0498. Min Act: -0.1662

Data Index: 1053386 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.8348. Min Act: -0.1659

Data Index: 107954 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.7166. Min Act: -0.1694

Data Index: 762198 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.5131. Min Act: -0.1644

Data Index: 363982 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.4950. Min Act: -0.1699

Data Index: 765362 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.3381. Min Act: -0.1524

Data Index: 576826 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.2667. Min Act: -0.1686

Data Index: 117123 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.1926. Min Act: -0.1700

Data Index: 279036 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.2146. Min Act: -0.1172

Data Index: 496474 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.1706. Min Act: -0.1699

Data Index: 8356 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.1395. Min Act: -0.0685

Data Index: 103320 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.0706. Min Act: -0.1700

Data Index: 760676 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.0772. Min Act: -0.1696

Data Index: 803719 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.0506. Min Act: -0.1688

Data Index: 32590 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 9.0498. Min Range: -9.0498

Max Act: 7.0029. Min Act: -0.1700

Data Index: 661412 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 9.0498. Min Range: -9.0498

Max Act: 6.9363. Min Act: -0.1698

Data Index: 646431 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 9.0498. Min Range: -9.0498

Max Act: 6.8732. Min Act: -0.1700

Data Index: 398139 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 9.0498. Min Range: -9.0498

Max Act: 6.8538. Min Act: -0.1700

Data Index: 1334908 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 9.0498. Min Range: -9.0498

Max Act: 6.7697. Min Act: -0.1694

Data Index: 726070 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 9.0498. Min Range: -9.0498

Max Act: 6.8060. Min Act: -0.1543

Data Index: 774372 (C4 (Web Text))

Max Activating Token Index: 126