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

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

Neuron 246 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: 4.0017. Min Range: -4.0017

Max Act: 4.0017. Min Act: -0.1700

Data Index: 1483887 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.9386. Min Act: -0.1700

Data Index: 1648570 (Python Code)

Max Activating Token Index: 429

Text #2

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.8919. Min Act: -0.1700

Data Index: 1507248 (Python Code)

Max Activating Token Index: 143

Text #3

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.7504. Min Act: -0.1700

Data Index: 1522261 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.7317. Min Act: -0.1700

Data Index: 1393302 (Python Code)

Max Activating Token Index: 952

Text #5

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.7090. Min Act: -0.1700

Data Index: 1288019 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.6650. Min Act: -0.1700

Data Index: 1626688 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5797. Min Act: -0.1700

Data Index: 1305524 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.6432. Min Act: -0.1700

Data Index: 1602720 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5869. Min Act: -0.1700

Data Index: 293346 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5966. Min Act: -0.1700

Data Index: 951717 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5692. Min Act: -0.1700

Data Index: 1451189 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5545. Min Act: -0.1700

Data Index: 459520 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5660. Min Act: -0.1700

Data Index: 438349 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5561. Min Act: -0.1700

Data Index: 197760 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5422. Min Act: -0.1700

Data Index: 1068879 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5629. Min Act: -0.1700

Data Index: 903276 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.4778. Min Act: -0.1700

Data Index: 473869 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.4798. Min Act: -0.1700

Data Index: 536572 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 4.0017. Min Range: -4.0017

Max Act: 3.5282. Min Act: -0.1700

Data Index: 1305433 (C4 (Web Text))

Max Activating Token Index: 353