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

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

Neuron 1488 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: 4.5493. Min Range: -4.5493

Max Act: 4.5493. Min Act: -0.1685

Data Index: 1559594 (Python Code)

Max Activating Token Index: 807

Text #1

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.5357. Min Act: -0.1698

Data Index: 1566664 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.3805. Min Act: -0.1699

Data Index: 1420802 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.3551. Min Act: -0.1485

Data Index: 519524 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.3693. Min Act: -0.1699

Data Index: 563671 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.3036. Min Act: -0.1700

Data Index: 926520 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.2457. Min Act: -0.1700

Data Index: 1632012 (Python Code)

Max Activating Token Index: 217

Text #7

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.2363. Min Act: -0.1683

Data Index: 1437181 (Python Code)

Max Activating Token Index: 313

Text #8

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.2126. Min Act: -0.1485

Data Index: 1361635 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.1798. Min Act: -0.1485

Data Index: 1515365 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.1566. Min Act: -0.1700

Data Index: 1179209 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.1265. Min Act: -0.1693

Data Index: 713179 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.1157. Min Act: -0.1485

Data Index: 1448920 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.1339. Min Act: -0.1700

Data Index: 1500212 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.1214. Min Act: -0.1700

Data Index: 1620697 (Python Code)

Max Activating Token Index: 994

Text #15

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.1362. Min Act: -0.1700

Data Index: 527941 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.1459. Min Act: -0.1700

Data Index: 1087958 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.0869. Min Act: -0.1485

Data Index: 1596839 (Python Code)

Max Activating Token Index: 187

Text #18

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.0916. Min Act: -0.1700

Data Index: 1420986 (Python Code)

Max Activating Token Index: 744

Text #19

Max Range: 4.5493. Min Range: -4.5493

Max Act: 4.1079. Min Act: -0.1485

Data Index: 1623326 (Python Code)

Max Activating Token Index: 518