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

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

Neuron 1314 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: 3.6409. Min Range: -3.6409

Max Act: 3.6409. Min Act: -0.1700

Data Index: 1582732 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.5950. Min Act: -0.1700

Data Index: 1467545 (Python Code)

Max Activating Token Index: 289

Text #2

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.5231. Min Act: -0.1700

Data Index: 1377812 (Python Code)

Max Activating Token Index: 607

Text #3

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.5047. Min Act: -0.1700

Data Index: 1022666 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4757. Min Act: -0.1700

Data Index: 1439383 (Python Code)

Max Activating Token Index: 547

Text #5

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4661. Min Act: -0.1700

Data Index: 60815 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4525. Min Act: -0.1700

Data Index: 1101395 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4473. Min Act: -0.1700

Data Index: 1437098 (Python Code)

Max Activating Token Index: 525

Text #8

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4293. Min Act: -0.1700

Data Index: 1483219 (Python Code)

Max Activating Token Index: 932

Text #9

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4104. Min Act: -0.1700

Data Index: 216433 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4093. Min Act: -0.1700

Data Index: 1559542 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4189. Min Act: -0.1700

Data Index: 1364696 (Python Code)

Max Activating Token Index: 703

Text #12

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3667. Min Act: -0.1700

Data Index: 1560447 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3772. Min Act: -0.1700

Data Index: 1470612 (Python Code)

Max Activating Token Index: 863

Text #14

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3535. Min Act: -0.1700

Data Index: 1390891 (Python Code)

Max Activating Token Index: 549

Text #15

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3621. Min Act: -0.1700

Data Index: 396027 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3547. Min Act: -0.1700

Data Index: 1216554 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3390. Min Act: -0.1700

Data Index: 1185596 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3443. Min Act: -0.1700

Data Index: 1399573 (Python Code)

Max Activating Token Index: 485

Text #19

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3446. Min Act: -0.1700

Data Index: 1453829 (Python Code)

Max Activating Token Index: 364