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

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

Neuron 1483 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.5452. Min Act: -0.1700

Data Index: 200619 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.3890. Min Act: -0.1700

Data Index: 1234407 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.3577. Min Act: -0.1700

Data Index: 633856 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.3577. Min Act: -0.1700

Data Index: 855700 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.2952. Min Act: -0.1700

Data Index: 237260 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.2952. Min Act: -0.1700

Data Index: 1038684 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.2952. Min Act: -0.1700

Data Index: 699440 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.2327. Min Act: -0.1700

Data Index: 1207005 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.2327. Min Act: -0.1700

Data Index: 1256763 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.1702. Min Act: -0.1700

Data Index: 751144 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.2015. Min Act: -0.1700

Data Index: 1350935 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.2015. Min Act: -0.1700

Data Index: 497592 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.1390. Min Act: -0.1700

Data Index: 293279 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.2015. Min Act: -0.1700

Data Index: 644848 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.1702. Min Act: -0.1700

Data Index: 478292 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.1702. Min Act: -0.1700

Data Index: 1298818 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.1390. Min Act: -0.1700

Data Index: 510589 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.1390. Min Act: -0.1700

Data Index: 645704 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.1077. Min Act: -0.1700

Data Index: 959845 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 5.5452. Min Range: -5.5452

Max Act: 5.1390. Min Act: -0.1700

Data Index: 278080 (C4 (Web Text))

Max Activating Token Index: 45