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

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

Neuron 1521 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: 4.5332. Min Range: -4.5332

Max Act: 4.5332. Min Act: -0.1699

Data Index: 146065 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.4755. Min Act: -0.1700

Data Index: 1200914 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.4745. Min Act: -0.1700

Data Index: 969213 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.3844. Min Act: -0.1654

Data Index: 1028458 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.1072. Min Act: -0.1700

Data Index: 1584912 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.1369. Min Act: -0.1700

Data Index: 1466222 (Python Code)

Max Activating Token Index: 149

Text #6

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.1194. Min Act: -0.1699

Data Index: 1359995 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.1384. Min Act: -0.1699

Data Index: 1375277 (Python Code)

Max Activating Token Index: 762

Text #8

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0648. Min Act: -0.1682

Data Index: 401788 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.1077. Min Act: -0.1700

Data Index: 450349 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0390. Min Act: -0.1696

Data Index: 933867 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0573. Min Act: -0.1700

Data Index: 1538472 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0619. Min Act: -0.1698

Data Index: 1144735 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0565. Min Act: -0.1700

Data Index: 1145339 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0256. Min Act: -0.1700

Data Index: 79857 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0109. Min Act: -0.1698

Data Index: 1562791 (Python Code)

Max Activating Token Index: 342

Text #16

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0321. Min Act: -0.1700

Data Index: 1538200 (Python Code)

Max Activating Token Index: 849

Text #17

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0178. Min Act: -0.1700

Data Index: 1368581 (Python Code)

Max Activating Token Index: 741

Text #18

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0266. Min Act: -0.1698

Data Index: 409455 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 4.5332. Min Range: -4.5332

Max Act: 4.0141. Min Act: -0.1696

Data Index: 571321 (C4 (Web Text))

Max Activating Token Index: 1023