Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1376 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.3412. Min Act: -0.1700

Data Index: 457943 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.3098. Min Act: -0.1700

Data Index: 1137368 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.3255. Min Act: -0.1700

Data Index: 1389788 (Python Code)

Max Activating Token Index: 540

Text #3

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.3098. Min Act: -0.1700

Data Index: 609882 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2941. Min Act: -0.1700

Data Index: 139329 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2941. Min Act: -0.1700

Data Index: 1426121 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2941. Min Act: -0.1700

Data Index: 1406219 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.3098. Min Act: -0.1700

Data Index: 178755 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2941. Min Act: -0.1700

Data Index: 587642 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2784. Min Act: -0.1700

Data Index: 426284 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2627. Min Act: -0.1700

Data Index: 1588921 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2784. Min Act: -0.1700

Data Index: 604200 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2627. Min Act: -0.1700

Data Index: 1319288 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2784. Min Act: -0.1700

Data Index: 78931 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2784. Min Act: -0.1700

Data Index: 822696 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2313. Min Act: -0.1700

Data Index: 1575964 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2470. Min Act: -0.1700

Data Index: 1591842 (Python Code)

Max Activating Token Index: 192

Text #17

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2313. Min Act: -0.1700

Data Index: 199053 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2313. Min Act: -0.1700

Data Index: 914207 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 3.3412. Min Range: -3.3412

Max Act: 3.2313. Min Act: -0.1700

Data Index: 749202 (C4 (Web Text))

Max Activating Token Index: 748