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

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

Neuron 1463 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: 3.3871. Min Range: -3.3871

Max Act: 3.3871. Min Act: -0.1700

Data Index: 1494703 (Python Code)

Max Activating Token Index: 653

Text #1

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2117. Min Act: -0.1700

Data Index: 1541019 (Python Code)

Max Activating Token Index: 654

Text #2

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2064. Min Act: -0.1700

Data Index: 1447220 (Python Code)

Max Activating Token Index: 314

Text #3

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1895. Min Act: -0.1700

Data Index: 1537067 (Python Code)

Max Activating Token Index: 185

Text #4

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1788. Min Act: -0.1700

Data Index: 1574885 (Python Code)

Max Activating Token Index: 709

Text #5

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1579. Min Act: -0.1700

Data Index: 1627539 (Python Code)

Max Activating Token Index: 473

Text #6

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1429. Min Act: -0.1700

Data Index: 1545451 (Python Code)

Max Activating Token Index: 625

Text #7

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1332. Min Act: -0.1700

Data Index: 1565267 (Python Code)

Max Activating Token Index: 430

Text #8

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1091. Min Act: -0.1700

Data Index: 1378832 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1091. Min Act: -0.1700

Data Index: 1437250 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0998. Min Act: -0.1700

Data Index: 1253588 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0852. Min Act: -0.1700

Data Index: 1457159 (Python Code)

Max Activating Token Index: 397

Text #12

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0480. Min Act: -0.1700

Data Index: 1376481 (Python Code)

Max Activating Token Index: 151

Text #13

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0500. Min Act: -0.1699

Data Index: 1248601 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0388. Min Act: -0.1700

Data Index: 1452679 (Python Code)

Max Activating Token Index: 218

Text #15

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0389. Min Act: -0.1700

Data Index: 487673 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0414. Min Act: -0.1700

Data Index: 1409851 (Python Code)

Max Activating Token Index: 729

Text #17

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0332. Min Act: -0.1691

Data Index: 546222 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0301. Min Act: -0.1689

Data Index: 1283634 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.0182. Min Act: -0.1699

Data Index: 1107432 (C4 (Web Text))

Max Activating Token Index: 394