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

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

Neuron 1646 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: 4.5168. Min Range: -4.5168

Max Act: 4.5168. Min Act: -0.1700

Data Index: 1382246 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.4719. Min Act: -0.1630

Data Index: 1391140 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.4628. Min Act: -0.1700

Data Index: 1380964 (Python Code)

Max Activating Token Index: 387

Text #3

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.4222. Min Act: -0.1183

Data Index: 1585807 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.4336. Min Act: -0.1364

Data Index: 1398542 (Python Code)

Max Activating Token Index: 385

Text #5

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.4171. Min Act: -0.1699

Data Index: 1479495 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.3848. Min Act: -0.1699

Data Index: 1396052 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.3422. Min Act: -0.1700

Data Index: 1405324 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.3550. Min Act: -0.1700

Data Index: 1652786 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2830. Min Act: -0.1183

Data Index: 1371731 (Python Code)

Max Activating Token Index: 31

Text #10

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2685. Min Act: -0.1700

Data Index: 1529409 (Python Code)

Max Activating Token Index: 343

Text #11

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2914. Min Act: -0.1700

Data Index: 1490041 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2818. Min Act: -0.1243

Data Index: 1625736 (Python Code)

Max Activating Token Index: 333

Text #13

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2474. Min Act: -0.1700

Data Index: 1585575 (Python Code)

Max Activating Token Index: 1005

Text #14

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2537. Min Act: -0.1697

Data Index: 1438266 (Python Code)

Max Activating Token Index: 771

Text #15

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2388. Min Act: -0.1700

Data Index: 1390458 (Python Code)

Max Activating Token Index: 1012

Text #16

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2238. Min Act: -0.1699

Data Index: 1549930 (Python Code)

Max Activating Token Index: 560

Text #17

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2476. Min Act: -0.1668

Data Index: 1394499 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.2161. Min Act: -0.1700

Data Index: 1608016 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 4.5168. Min Range: -4.5168

Max Act: 4.1856. Min Act: -0.1183

Data Index: 1380010 (Python Code)

Max Activating Token Index: 273