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

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

Neuron 1686 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: 3.3247. Min Range: -3.3247

Max Act: 3.3247. Min Act: -0.1700

Data Index: 1622085 (Python Code)

Max Activating Token Index: 356

Text #1

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.2441. Min Act: -0.1699

Data Index: 1645303 (Python Code)

Max Activating Token Index: 1016

Text #2

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.1729. Min Act: -0.1700

Data Index: 1361745 (Python Code)

Max Activating Token Index: 217

Text #3

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.1460. Min Act: -0.1700

Data Index: 1440176 (Python Code)

Max Activating Token Index: 146

Text #4

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.1258. Min Act: -0.1700

Data Index: 525181 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.1195. Min Act: -0.1691

Data Index: 375947 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0992. Min Act: -0.1700

Data Index: 1649083 (Python Code)

Max Activating Token Index: 715

Text #7

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.1014. Min Act: -0.1700

Data Index: 1467782 (Python Code)

Max Activating Token Index: 214

Text #8

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1577527 (Python Code)

Max Activating Token Index: 485

Text #9

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0736. Min Act: -0.1699

Data Index: 1417606 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0695. Min Act: -0.1700

Data Index: 1625018 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0576. Min Act: -0.1700

Data Index: 1280409 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0517. Min Act: -0.1700

Data Index: 1377275 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0564. Min Act: -0.1700

Data Index: 1499993 (Python Code)

Max Activating Token Index: 431

Text #14

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0604. Min Act: -0.1700

Data Index: 1438323 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0202. Min Act: -0.1698

Data Index: 1536981 (Python Code)

Max Activating Token Index: 732

Text #16

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0335. Min Act: -0.1700

Data Index: 1428746 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0214. Min Act: -0.1699

Data Index: 1400173 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0139. Min Act: -0.1700

Data Index: 897966 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0197. Min Act: -0.1682

Data Index: 514115 (C4 (Web Text))

Max Activating Token Index: 831