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

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

Neuron 1105 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: 3.8266. Min Range: -3.8266

Max Act: 3.8266. Min Act: -0.1700

Data Index: 1545660 (Python Code)

Max Activating Token Index: 812

Text #1

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.8263. Min Act: -0.1700

Data Index: 1607987 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.7631. Min Act: -0.1700

Data Index: 1402468 (Python Code)

Max Activating Token Index: 592

Text #3

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.6572. Min Act: -0.1700

Data Index: 1522687 (Python Code)

Max Activating Token Index: 379

Text #4

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.5548. Min Act: -0.1700

Data Index: 1600211 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.5354. Min Act: -0.1700

Data Index: 1528228 (Python Code)

Max Activating Token Index: 731

Text #6

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.5328. Min Act: -0.1700

Data Index: 1444444 (Python Code)

Max Activating Token Index: 388

Text #7

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.5341. Min Act: -0.1700

Data Index: 1614501 (Python Code)

Max Activating Token Index: 820

Text #8

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.5108. Min Act: -0.1700

Data Index: 1404996 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1608821 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.5346. Min Act: -0.1700

Data Index: 1637720 (Python Code)

Max Activating Token Index: 363

Text #11

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.4992. Min Act: -0.1700

Data Index: 1648223 (Python Code)

Max Activating Token Index: 661

Text #12

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.4947. Min Act: -0.1700

Data Index: 1611998 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.4842. Min Act: -0.1700

Data Index: 1585989 (Python Code)

Max Activating Token Index: 938

Text #14

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.4974. Min Act: -0.1700

Data Index: 1391381 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.4684. Min Act: -0.1700

Data Index: 1390827 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.4619. Min Act: -0.1700

Data Index: 1507262 (Python Code)

Max Activating Token Index: 458

Text #17

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.4812. Min Act: -0.1700

Data Index: 1477906 (Python Code)

Max Activating Token Index: 185

Text #18

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.4844. Min Act: -0.1700

Data Index: 1592766 (Python Code)

Max Activating Token Index: 940

Text #19

Max Range: 3.8266. Min Range: -3.8266

Max Act: 3.4431. Min Act: -0.1700

Data Index: 1380593 (Python Code)

Max Activating Token Index: 88