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

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

Neuron 1363 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.2624. Min Act: -0.1700

Data Index: 1166076 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.1999. Min Act: -0.1700

Data Index: 582626 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.1686. Min Act: -0.1700

Data Index: 968562 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.1374. Min Act: -0.1700

Data Index: 637367 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.1374. Min Act: -0.1700

Data Index: 538223 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.1061. Min Act: -0.1700

Data Index: 714663 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.1061. Min Act: -0.1700

Data Index: 214852 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0749. Min Act: -0.1700

Data Index: 98869 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.1374. Min Act: -0.1700

Data Index: 1024830 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0749. Min Act: -0.1700

Data Index: 553422 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0436. Min Act: -0.1700

Data Index: 1133680 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.1061. Min Act: -0.1700

Data Index: 566261 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.1061. Min Act: -0.1700

Data Index: 524397 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0749. Min Act: -0.1700

Data Index: 156640 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0124. Min Act: -0.1700

Data Index: 867704 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0436. Min Act: -0.1700

Data Index: 700261 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0749. Min Act: -0.1700

Data Index: 1054795 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0749. Min Act: -0.1700

Data Index: 608243 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0436. Min Act: -0.1700

Data Index: 136542 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 5.2624. Min Range: -5.2624

Max Act: 5.0124. Min Act: -0.1700

Data Index: 566942 (C4 (Web Text))

Max Activating Token Index: 202