Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1315 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.4881. Min Act: -0.1700

Data Index: 724332 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3627. Min Act: -0.1699

Data Index: 357008 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3784. Min Act: -0.1700

Data Index: 377125 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3940. Min Act: -0.1696

Data Index: 436594 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3627. Min Act: -0.1700

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3470. Min Act: -0.1700

Data Index: 1338984 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3627. Min Act: -0.1700

Data Index: 214541 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3156. Min Act: -0.1700

Data Index: 866821 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3470. Min Act: -0.1697

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3156. Min Act: -0.1700

Data Index: 448880 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3156. Min Act: -0.1700

Data Index: 65104 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.2999. Min Act: -0.1699

Data Index: 453735 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3156. Min Act: -0.1700

Data Index: 234467 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.2684. Min Act: -0.1700

Data Index: 1004159 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.2527. Min Act: -0.1700

Data Index: 414634 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.2842. Min Act: -0.1700

Data Index: 28699 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.2842. Min Act: -0.1688

Data Index: 739922 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.3156. Min Act: -0.1686

Data Index: 801071 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.2527. Min Act: -0.1700

Data Index: 11462 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 3.4881. Min Range: -3.4881

Max Act: 3.2370. Min Act: -0.1700

Data Index: 776073 (C4 (Web Text))

Max Activating Token Index: 515