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

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

Neuron 66 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: 4.4874. Min Range: -4.4874

Max Act: 4.4874. Min Act: -0.1699

Data Index: 450649 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4384. Min Act: -0.1697

Data Index: 1541462 (Python Code)

Max Activating Token Index: 579

Text #2

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3780. Min Act: -0.1694

Data Index: 821003 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3541. Min Act: -0.1699

Data Index: 1466162 (Python Code)

Max Activating Token Index: 534

Text #4

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3268. Min Act: -0.1700

Data Index: 1490288 (Python Code)

Max Activating Token Index: 802

Text #5

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.2971. Min Act: -0.1515

Data Index: 1511697 (Python Code)

Max Activating Token Index: 881

Text #6

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.3089. Min Act: -0.1515

Data Index: 1590456 (Python Code)

Max Activating Token Index: 171

Text #7

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.2888. Min Act: -0.1698

Data Index: 1287461 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.2895. Min Act: -0.1700

Data Index: 1586697 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.2930. Min Act: -0.1699

Data Index: 1567430 (Python Code)

Max Activating Token Index: 990

Text #10

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.2593. Min Act: -0.1699

Data Index: 1526658 (Python Code)

Max Activating Token Index: 368

Text #11

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.2321. Min Act: -0.1700

Data Index: 1496017 (Python Code)

Max Activating Token Index: 463

Text #12

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.2274. Min Act: -0.1700

Data Index: 1616942 (Python Code)

Max Activating Token Index: 551

Text #13

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.2292. Min Act: -0.1700

Data Index: 1433561 (Python Code)

Max Activating Token Index: 1018

Text #14

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.2323. Min Act: -0.1696

Data Index: 1409415 (Python Code)

Max Activating Token Index: 507

Text #15

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.1636. Min Act: -0.1696

Data Index: 1394682 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.1653. Min Act: -0.1647

Data Index: 1548218 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.1548. Min Act: -0.1699

Data Index: 1170049 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.1353. Min Act: -0.1699

Data Index: 1583346 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.1449. Min Act: -0.1699

Data Index: 1457139 (Python Code)

Max Activating Token Index: 626