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

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

Neuron 913 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: 4.9483. Min Range: -4.9483

Max Act: 4.9483. Min Act: -0.1700

Data Index: 1539685 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.6214. Min Act: -0.1700

Data Index: 1555282 (Python Code)

Max Activating Token Index: 821

Text #2

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.6229. Min Act: -0.1700

Data Index: 1422153 (Python Code)

Max Activating Token Index: 80

Text #3

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.5686. Min Act: -0.1700

Data Index: 1527797 (Python Code)

Max Activating Token Index: 322

Text #4

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.4814. Min Act: -0.1700

Data Index: 1601406 (Python Code)

Max Activating Token Index: 635

Text #5

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.5269. Min Act: -0.1700

Data Index: 1454459 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.5214. Min Act: -0.1700

Data Index: 1585238 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.4563. Min Act: -0.1700

Data Index: 1565496 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.4623. Min Act: -0.1700

Data Index: 1483956 (Python Code)

Max Activating Token Index: 611

Text #9

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.4432. Min Act: -0.1700

Data Index: 1624606 (Python Code)

Max Activating Token Index: 536

Text #10

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.4698. Min Act: -0.1700

Data Index: 1652407 (Python Code)

Max Activating Token Index: 693

Text #11

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.4494. Min Act: -0.1700

Data Index: 1570414 (Python Code)

Max Activating Token Index: 671

Text #12

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.4060. Min Act: -0.1700

Data Index: 1425867 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.3985. Min Act: -0.1700

Data Index: 1620979 (Python Code)

Max Activating Token Index: 793

Text #14

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.3643. Min Act: -0.1700

Data Index: 1541291 (Python Code)

Max Activating Token Index: 682

Text #15

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.3644. Min Act: -0.1700

Data Index: 1638099 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.3349. Min Act: -0.1700

Data Index: 68898 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.3429. Min Act: -0.1700

Data Index: 549950 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.3650. Min Act: -0.1700

Data Index: 1449052 (Python Code)

Max Activating Token Index: 658

Text #19

Max Range: 4.9483. Min Range: -4.9483

Max Act: 4.3403. Min Act: -0.1700

Data Index: 1560378 (Python Code)

Max Activating Token Index: 218