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

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

Neuron 325 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: 4.3859. Min Range: -4.3859

Max Act: 4.3778. Min Act: -0.1699

Data Index: 575480 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.3859. Min Act: -0.1699

Data Index: 373755 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.3599. Min Act: -0.1700

Data Index: 596746 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.2912. Min Act: -0.1700

Data Index: 919154 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.2757. Min Act: -0.1699

Data Index: 1463180 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.2658. Min Act: -0.1700

Data Index: 1363921 (Python Code)

Max Activating Token Index: 828

Text #6

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.2275. Min Act: -0.1699

Data Index: 811586 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.2439. Min Act: -0.1700

Data Index: 317750 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.2056. Min Act: -0.1700

Data Index: 177838 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.2139. Min Act: -0.1695

Data Index: 1476126 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.1521. Min Act: -0.1699

Data Index: 996976 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.1255. Min Act: -0.1697

Data Index: 1420522 (Python Code)

Max Activating Token Index: 831

Text #12

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.1564. Min Act: -0.1699

Data Index: 480359 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.1211. Min Act: -0.1700

Data Index: 554236 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.1180. Min Act: -0.1699

Data Index: 1340864 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.0767. Min Act: -0.1700

Data Index: 1184346 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.0801. Min Act: -0.1700

Data Index: 828574 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.0846. Min Act: -0.1700

Data Index: 589189 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.0879. Min Act: -0.1695

Data Index: 217716 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 4.3859. Min Range: -4.3859

Max Act: 4.0494. Min Act: -0.1481

Data Index: 1484968 (Python Code)

Max Activating Token Index: 21