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

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

Neuron 1443 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: 3.1677. Min Range: -3.1677

Max Act: 3.1677. Min Act: -0.1700

Data Index: 190610 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.1509. Min Act: -0.1700

Data Index: 1499370 (Python Code)

Max Activating Token Index: 806

Text #2

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.1315. Min Act: -0.1700

Data Index: 1635659 (Python Code)

Max Activating Token Index: 217

Text #3

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1307820 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0345. Min Act: -0.1700

Data Index: 643926 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0735. Min Act: -0.1700

Data Index: 1256807 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0599. Min Act: -0.1700

Data Index: 1210334 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0322. Min Act: -0.1700

Data Index: 1454258 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0303. Min Act: -0.1700

Data Index: 231915 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0161. Min Act: -0.1700

Data Index: 1560716 (Python Code)

Max Activating Token Index: 455

Text #10

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0204. Min Act: -0.1700

Data Index: 71877 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0059. Min Act: -0.1700

Data Index: 1468020 (Python Code)

Max Activating Token Index: 286

Text #12

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.9912. Min Act: -0.1700

Data Index: 1409590 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.9731. Min Act: -0.1700

Data Index: 1543846 (Python Code)

Max Activating Token Index: 665

Text #14

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.9738. Min Act: -0.1700

Data Index: 676570 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.9601. Min Act: -0.1700

Data Index: 1651010 (Python Code)

Max Activating Token Index: 115

Text #16

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.9408. Min Act: -0.1700

Data Index: 943418 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.9520. Min Act: -0.1700

Data Index: 1107296 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.9494. Min Act: -0.1700

Data Index: 1497305 (Python Code)

Max Activating Token Index: 336

Text #19

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.9406. Min Act: -0.1700

Data Index: 1092627 (C4 (Web Text))

Max Activating Token Index: 657