Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 554 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.2370. Min Range: -4.2370

Max Act: 4.2370. Min Act: -0.1700

Data Index: 1472019 (Python Code)

Max Activating Token Index: 328

Text #1

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.9923. Min Act: -0.1700

Data Index: 1377873 (Python Code)

Max Activating Token Index: 916

Text #2

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.9704. Min Act: -0.1699

Data Index: 1364038 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.9095. Min Act: -0.1700

Data Index: 1530080 (Python Code)

Max Activating Token Index: 607

Text #4

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.8881. Min Act: -0.1699

Data Index: 1612544 (Python Code)

Max Activating Token Index: 366

Text #5

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.8037. Min Act: -0.1699

Data Index: 424476 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.8031. Min Act: -0.1700

Data Index: 1529695 (Python Code)

Max Activating Token Index: 953

Text #7

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7698. Min Act: -0.1686

Data Index: 1517626 (Python Code)

Max Activating Token Index: 457

Text #8

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7983. Min Act: -0.1700

Data Index: 1568285 (Python Code)

Max Activating Token Index: 620

Text #9

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7432. Min Act: -0.1699

Data Index: 1516802 (Python Code)

Max Activating Token Index: 788

Text #10

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7074. Min Act: -0.1698

Data Index: 558950 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7249. Min Act: -0.1698

Data Index: 1403905 (Python Code)

Max Activating Token Index: 532

Text #12

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7331. Min Act: -0.1700

Data Index: 1646740 (Python Code)

Max Activating Token Index: 363

Text #13

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7266. Min Act: -0.1693

Data Index: 1508997 (Python Code)

Max Activating Token Index: 329

Text #14

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7287. Min Act: -0.1700

Data Index: 1647300 (Python Code)

Max Activating Token Index: 758

Text #15

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7129. Min Act: -0.1697

Data Index: 907587 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7114. Min Act: -0.1700

Data Index: 357808 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.6951. Min Act: -0.1700

Data Index: 1622172 (Python Code)

Max Activating Token Index: 724

Text #18

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.6774. Min Act: -0.1546

Data Index: 1528820 (Python Code)

Max Activating Token Index: 869

Text #19

Max Range: 4.2370. Min Range: -4.2370

Max Act: 3.7104. Min Act: -0.1699

Data Index: 1523469 (Python Code)

Max Activating Token Index: 626