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

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

Neuron 1723 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: 3.6528. Min Range: -3.6528

Max Act: 3.6528. Min Act: -0.1699

Data Index: 453697 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4727. Min Act: -0.1652

Data Index: 425806 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4520. Min Act: -0.1699

Data Index: 1409290 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4434. Min Act: -0.1700

Data Index: 1413333 (Python Code)

Max Activating Token Index: 690

Text #4

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4148. Min Act: -0.1687

Data Index: 991986 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3652. Min Act: -0.1670

Data Index: 194900 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3650. Min Act: -0.1697

Data Index: 1652024 (Python Code)

Max Activating Token Index: 922

Text #7

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1456530 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3386. Min Act: -0.1694

Data Index: 14003 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3398. Min Act: -0.1697

Data Index: 1568024 (Python Code)

Max Activating Token Index: 551

Text #10

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3438. Min Act: -0.1699

Data Index: 1418356 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3394. Min Act: -0.1699

Data Index: 1504554 (Python Code)

Max Activating Token Index: 509

Text #12

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3413. Min Act: -0.1698

Data Index: 1493065 (Python Code)

Max Activating Token Index: 181

Text #13

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3316. Min Act: -0.1700

Data Index: 76889 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3341. Min Act: -0.1698

Data Index: 1271336 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3433. Min Act: -0.1677

Data Index: 842719 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3064. Min Act: -0.1700

Data Index: 1604186 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.2951. Min Act: -0.1692

Data Index: 1624524 (Python Code)

Max Activating Token Index: 689

Text #18

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3052. Min Act: -0.1700

Data Index: 1387577 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.2938. Min Act: -0.1700

Data Index: 1652752 (Python Code)

Max Activating Token Index: 581