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

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

Neuron 745 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: 4.4657. Min Range: -4.4657

Max Act: 4.4657. Min Act: -0.1700

Data Index: 1622218 (Python Code)

Max Activating Token Index: 137

Text #1

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.4253. Min Act: -0.1699

Data Index: 1552631 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.3971. Min Act: -0.1700

Data Index: 1484935 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.3400. Min Act: -0.1698

Data Index: 1386517 (Python Code)

Max Activating Token Index: 684

Text #4

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.2696. Min Act: -0.1697

Data Index: 1439324 (Python Code)

Max Activating Token Index: 994

Text #5

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.2392. Min Act: -0.1700

Data Index: 1413405 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.2357. Min Act: -0.1700

Data Index: 1439900 (Python Code)

Max Activating Token Index: 70

Text #7

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.2124. Min Act: -0.1697

Data Index: 1496201 (Python Code)

Max Activating Token Index: 804

Text #8

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.2054. Min Act: -0.1700

Data Index: 1397149 (Python Code)

Max Activating Token Index: 373

Text #9

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.2099. Min Act: -0.1699

Data Index: 1499295 (Python Code)

Max Activating Token Index: 767

Text #10

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.1677. Min Act: -0.1700

Data Index: 1612868 (Python Code)

Max Activating Token Index: 219

Text #11

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.1550. Min Act: -0.1700

Data Index: 1603706 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.1324. Min Act: -0.1700

Data Index: 1567887 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.1642. Min Act: -0.1700

Data Index: 1484971 (Python Code)

Max Activating Token Index: 881

Text #14

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.0509. Min Act: -0.1699

Data Index: 1566565 (Python Code)

Max Activating Token Index: 274

Text #15

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.0593. Min Act: -0.1648

Data Index: 1599337 (Python Code)

Max Activating Token Index: 809

Text #16

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.0477. Min Act: -0.1700

Data Index: 1369509 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.0371. Min Act: -0.1697

Data Index: 1521275 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.0523. Min Act: -0.1700

Data Index: 1394841 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.0834. Min Act: -0.1694

Data Index: 1619761 (Python Code)

Max Activating Token Index: 63