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

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

Neuron 1894 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: 15.9637. Min Range: -15.9637

Max Act: 15.9637. Min Act: -0.1699

Data Index: 543038 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 15.9637. Min Range: -15.9637

Max Act: 15.0833. Min Act: -0.1700

Data Index: 1436275 (Python Code)

Max Activating Token Index: 708

Text #2

Max Range: 15.9637. Min Range: -15.9637

Max Act: 15.0224. Min Act: -0.1699

Data Index: 806408 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.8999. Min Act: -0.1700

Data Index: 1629689 (Python Code)

Max Activating Token Index: 521

Text #4

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.8237. Min Act: -0.1700

Data Index: 1404851 (Python Code)

Max Activating Token Index: 188

Text #5

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.8156. Min Act: -0.1550

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.8159. Min Act: -0.1697

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.4417. Min Act: -0.1700

Data Index: 1548149 (Python Code)

Max Activating Token Index: 537

Text #8

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.3418. Min Act: -0.1700

Data Index: 1520583 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.2441. Min Act: -0.1700

Data Index: 1566267 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.1100. Min Act: -0.1700

Data Index: 1592952 (Python Code)

Max Activating Token Index: 813

Text #11

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.1151. Min Act: -0.1700

Data Index: 1507974 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.0680. Min Act: -0.1699

Data Index: 611675 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.0773. Min Act: -0.1700

Data Index: 45430 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 15.9637. Min Range: -15.9637

Max Act: 13.9930. Min Act: -0.1700

Data Index: 1416613 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 15.9637. Min Range: -15.9637

Max Act: 14.0024. Min Act: -0.1699

Data Index: 427553 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 15.9637. Min Range: -15.9637

Max Act: 13.9940. Min Act: -0.1700

Data Index: 493417 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 15.9637. Min Range: -15.9637

Max Act: 13.8802. Min Act: -0.1700

Data Index: 1558640 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 15.9637. Min Range: -15.9637

Max Act: 13.9022. Min Act: -0.1698

Data Index: 1007764 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 15.9637. Min Range: -15.9637

Max Act: 13.8864. Min Act: -0.1700

Data Index: 1363578 (Python Code)

Max Activating Token Index: 728