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

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

Neuron 412 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: 5.8969. Min Range: -5.8969

Max Act: 5.8969. Min Act: -0.1700

Data Index: 993407 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.8969. Min Act: -0.1700

Data Index: 89836 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.5219. Min Act: -0.1700

Data Index: 676416 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.4282. Min Act: -0.1700

Data Index: 296035 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.3344. Min Act: -0.1700

Data Index: 285037 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.3032. Min Act: -0.1700

Data Index: 786346 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.3344. Min Act: -0.1700

Data Index: 725402 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.3032. Min Act: -0.1700

Data Index: 128433 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2719. Min Act: -0.1700

Data Index: 942152 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2719. Min Act: -0.1700

Data Index: 541807 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2407. Min Act: -0.1700

Data Index: 681056 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2407. Min Act: -0.1700

Data Index: 704373 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2407. Min Act: -0.1700

Data Index: 108514 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2094. Min Act: -0.1700

Data Index: 1277428 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2094. Min Act: -0.1700

Data Index: 330334 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2094. Min Act: -0.1700

Data Index: 1339554 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.1782. Min Act: -0.1700

Data Index: 911113 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.1469. Min Act: -0.1700

Data Index: 568359 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2094. Min Act: -0.1700

Data Index: 571779 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 5.8969. Min Range: -5.8969

Max Act: 5.2094. Min Act: -0.1700

Data Index: 375491 (C4 (Web Text))

Max Activating Token Index: 707