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

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

Neuron 845 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: 4.9116. Min Range: -4.9116

Max Act: 4.9116. Min Act: -0.1700

Data Index: 452531 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.8856. Min Act: -0.1700

Data Index: 1619500 (Python Code)

Max Activating Token Index: 799

Text #2

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.8714. Min Act: -0.1699

Data Index: 1584375 (Python Code)

Max Activating Token Index: 512

Text #3

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.7982. Min Act: -0.1530

Data Index: 1499170 (Python Code)

Max Activating Token Index: 946

Text #4

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.7677. Min Act: -0.1700

Data Index: 1363863 (Python Code)

Max Activating Token Index: 959

Text #5

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.7777. Min Act: -0.1699

Data Index: 1582068 (Python Code)

Max Activating Token Index: 292

Text #6

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.7165. Min Act: -0.1700

Data Index: 332400 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.7624. Min Act: -0.1700

Data Index: 1538721 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.7196. Min Act: -0.1700

Data Index: 1054979 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.6532. Min Act: -0.1700

Data Index: 124266 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.6374. Min Act: -0.1699

Data Index: 1443038 (Python Code)

Max Activating Token Index: 788

Text #11

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.6602. Min Act: -0.1661

Data Index: 1566939 (Python Code)

Max Activating Token Index: 710

Text #12

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.6583. Min Act: -0.1697

Data Index: 1516332 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.5990. Min Act: -0.1700

Data Index: 1440463 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.6260. Min Act: -0.1700

Data Index: 1591802 (Python Code)

Max Activating Token Index: 438

Text #15

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.5834. Min Act: -0.1297

Data Index: 1469782 (Python Code)

Max Activating Token Index: 646

Text #16

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.5771. Min Act: -0.1700

Data Index: 1516134 (Python Code)

Max Activating Token Index: 361

Text #17

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.5738. Min Act: -0.1700

Data Index: 1579757 (Python Code)

Max Activating Token Index: 428

Text #18

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.5693. Min Act: -0.1700

Data Index: 1409641 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 4.9116. Min Range: -4.9116

Max Act: 4.5463. Min Act: -0.1700

Data Index: 156343 (C4 (Web Text))

Max Activating Token Index: 852