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

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

Neuron 1475 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: 4.6133. Min Range: -4.6133

Max Act: 4.6133. Min Act: -0.1699

Data Index: 701437 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.4796. Min Act: -0.1700

Data Index: 361878 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.3304. Min Act: -0.1700

Data Index: 328716 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.2611. Min Act: -0.1700

Data Index: 484534 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.2382. Min Act: -0.1699

Data Index: 523086 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.2062. Min Act: -0.1520

Data Index: 874066 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.2293. Min Act: -0.1700

Data Index: 481174 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.2137. Min Act: -0.1699

Data Index: 1110386 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1685. Min Act: -0.1700

Data Index: 644365 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1798. Min Act: -0.1616

Data Index: 1231669 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1762. Min Act: -0.1693

Data Index: 174028 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1557. Min Act: -0.1550

Data Index: 1611316 (Python Code)

Max Activating Token Index: 703

Text #12

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1589. Min Act: -0.1700

Data Index: 249641 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1698. Min Act: -0.1700

Data Index: 754408 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1482. Min Act: -0.1700

Data Index: 449250 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1380. Min Act: -0.1606

Data Index: 661108 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1499. Min Act: -0.1700

Data Index: 949135 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1144. Min Act: -0.1700

Data Index: 298238 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1334. Min Act: -0.1700

Data Index: 519968 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 4.6133. Min Range: -4.6133

Max Act: 4.1287. Min Act: -0.1700

Data Index: 483887 (C4 (Web Text))

Max Activating Token Index: 507