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

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

Neuron 54 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: 3.4381. Min Range: -3.4381

Max Act: 3.4381. Min Act: -0.1700

Data Index: 952663 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2811. Min Act: -0.1700

Data Index: 154356 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2634. Min Act: -0.1700

Data Index: 136005 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2710. Min Act: -0.1700

Data Index: 373923 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2550. Min Act: -0.1700

Data Index: 512696 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2617. Min Act: -0.1700

Data Index: 38172 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2627. Min Act: -0.1700

Data Index: 313925 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2296. Min Act: -0.1700

Data Index: 1100485 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1227160 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1856. Min Act: -0.1700

Data Index: 160204 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1727. Min Act: -0.1700

Data Index: 1098324 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1960. Min Act: -0.1700

Data Index: 1129219 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1856. Min Act: -0.1700

Data Index: 839593 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1706. Min Act: -0.1700

Data Index: 20022 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1667. Min Act: -0.1700

Data Index: 1337020 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1459. Min Act: -0.1700

Data Index: 982924 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1555. Min Act: -0.1700

Data Index: 381966 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1461. Min Act: -0.1700

Data Index: 951697 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1577. Min Act: -0.1700

Data Index: 635506 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.1322. Min Act: -0.1700

Data Index: 1372730 (Python Code)

Max Activating Token Index: 35