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

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

Neuron 897 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: 3.5181. Min Range: -3.5181

Max Act: 3.5181. Min Act: -0.1695

Data Index: 1619401 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4712. Min Act: -0.1700

Data Index: 1523547 (Python Code)

Max Activating Token Index: 923

Text #2

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4403. Min Act: -0.1699

Data Index: 1566490 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4151. Min Act: -0.1699

Data Index: 1462986 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3965. Min Act: -0.1697

Data Index: 1580542 (Python Code)

Max Activating Token Index: 1018

Text #5

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3750. Min Act: -0.0562

Data Index: 1401727 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3784. Min Act: -0.1640

Data Index: 1391726 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3771. Min Act: -0.1694

Data Index: 1557379 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3619. Min Act: -0.1691

Data Index: 1586354 (Python Code)

Max Activating Token Index: 321

Text #9

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3478. Min Act: -0.1286

Data Index: 1401923 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3566. Min Act: -0.1698

Data Index: 1512153 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3351. Min Act: -0.1700

Data Index: 1580724 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3234. Min Act: -0.1688

Data Index: 1466773 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3131. Min Act: -0.1700

Data Index: 1396224 (Python Code)

Max Activating Token Index: 442

Text #14

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3033. Min Act: -0.1695

Data Index: 1649600 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3289. Min Act: -0.1606

Data Index: 1467892 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3034. Min Act: -0.1700

Data Index: 1371858 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.2883. Min Act: -0.1700

Data Index: 1490384 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3079. Min Act: -0.1700

Data Index: 1601829 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.3116. Min Act: -0.1472

Data Index: 1515790 (Python Code)

Max Activating Token Index: 764