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

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

Neuron 1867 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: 4.2381. Min Range: -4.2381

Max Act: 4.2381. Min Act: -0.1697

Data Index: 1537814 (Python Code)

Max Activating Token Index: 127

Text #1

Max Range: 4.2381. Min Range: -4.2381

Max Act: 4.1219. Min Act: -0.1688

Data Index: 1373706 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 4.2381. Min Range: -4.2381

Max Act: 4.1031. Min Act: -0.1700

Data Index: 1400604 (Python Code)

Max Activating Token Index: 943

Text #3

Max Range: 4.2381. Min Range: -4.2381

Max Act: 4.0825. Min Act: -0.1636

Data Index: 1533184 (Python Code)

Max Activating Token Index: 261

Text #4

Max Range: 4.2381. Min Range: -4.2381

Max Act: 4.0893. Min Act: -0.1700

Data Index: 1528937 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 4.2381. Min Range: -4.2381

Max Act: 4.0326. Min Act: -0.1700

Data Index: 1451926 (Python Code)

Max Activating Token Index: 366

Text #6

Max Range: 4.2381. Min Range: -4.2381

Max Act: 4.0178. Min Act: -0.1700

Data Index: 1618223 (Python Code)

Max Activating Token Index: 557

Text #7

Max Range: 4.2381. Min Range: -4.2381

Max Act: 4.0218. Min Act: -0.1689

Data Index: 1579477 (Python Code)

Max Activating Token Index: 417

Text #8

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9988. Min Act: -0.1700

Data Index: 1477494 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9976. Min Act: -0.1700

Data Index: 1482429 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9695. Min Act: -0.1691

Data Index: 1617956 (Python Code)

Max Activating Token Index: 157

Text #11

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9760. Min Act: -0.1700

Data Index: 1433465 (Python Code)

Max Activating Token Index: 490

Text #12

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9553. Min Act: -0.1698

Data Index: 1636278 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9562. Min Act: -0.1671

Data Index: 1361104 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9331. Min Act: -0.1699

Data Index: 1541418 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.8995. Min Act: -0.1700

Data Index: 1370938 (Python Code)

Max Activating Token Index: 887

Text #16

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9079. Min Act: -0.1700

Data Index: 1426368 (Python Code)

Max Activating Token Index: 744

Text #17

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9131. Min Act: -0.1700

Data Index: 1469657 (Python Code)

Max Activating Token Index: 604

Text #18

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9226. Min Act: -0.1697

Data Index: 1526765 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 4.2381. Min Range: -4.2381

Max Act: 3.9130. Min Act: -0.1700

Data Index: 1555204 (Python Code)

Max Activating Token Index: 908