Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 729 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.4800. Min Act: -0.1700

Data Index: 314993 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.4173. Min Act: -0.1700

Data Index: 639112 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.3232. Min Act: -0.1700

Data Index: 469308 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.3389. Min Act: -0.1700

Data Index: 1018801 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.2760. Min Act: -0.1700

Data Index: 518459 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.3075. Min Act: -0.1700

Data Index: 1067880 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.2446. Min Act: -0.1700

Data Index: 1012399 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.2446. Min Act: -0.1700

Data Index: 357568 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.2289. Min Act: -0.1700

Data Index: 652906 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.2132. Min Act: -0.1700

Data Index: 409640 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.2132. Min Act: -0.1700

Data Index: 685346 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.1974. Min Act: -0.1700

Data Index: 1207995 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.1974. Min Act: -0.1700

Data Index: 1288496 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.1974. Min Act: -0.1700

Data Index: 857451 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.1660. Min Act: -0.1700

Data Index: 339282 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.2132. Min Act: -0.1700

Data Index: 309353 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.1974. Min Act: -0.1700

Data Index: 442820 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.1502. Min Act: -0.1700

Data Index: 1619160 (Python Code)

Max Activating Token Index: 400

Text #18

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.1660. Min Act: -0.1700

Data Index: 606666 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 3.4800. Min Range: -3.4800

Max Act: 3.1660. Min Act: -0.1700

Data Index: 63345 (C4 (Web Text))

Max Activating Token Index: 1006