Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 281 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.4882. Min Act: -0.1700

Data Index: 1447097 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3944. Min Act: -0.1700

Data Index: 1432514 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3632. Min Act: -0.1700

Data Index: 1613868 (Python Code)

Max Activating Token Index: 405

Text #3

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3632. Min Act: -0.1700

Data Index: 1512565 (Python Code)

Max Activating Token Index: 388

Text #4

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3632. Min Act: -0.1700

Data Index: 1506609 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3632. Min Act: -0.1700

Data Index: 1389987 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3632. Min Act: -0.1700

Data Index: 1363311 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3007. Min Act: -0.1700

Data Index: 1583562 (Python Code)

Max Activating Token Index: 244

Text #8

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2694. Min Act: -0.1700

Data Index: 1513971 (Python Code)

Max Activating Token Index: 270

Text #9

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3319. Min Act: -0.1700

Data Index: 1455093 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3319. Min Act: -0.1700

Data Index: 1642022 (Python Code)

Max Activating Token Index: 891

Text #11

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3007. Min Act: -0.1700

Data Index: 1372325 (Python Code)

Max Activating Token Index: 266

Text #12

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3319. Min Act: -0.1700

Data Index: 1413997 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3007. Min Act: -0.1700

Data Index: 1449672 (Python Code)

Max Activating Token Index: 274

Text #14

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2694. Min Act: -0.1700

Data Index: 1612434 (Python Code)

Max Activating Token Index: 310

Text #15

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3319. Min Act: -0.1700

Data Index: 1380661 (Python Code)

Max Activating Token Index: 705

Text #16

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2694. Min Act: -0.1700

Data Index: 1408964 (Python Code)

Max Activating Token Index: 258

Text #17

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2382. Min Act: -0.1700

Data Index: 1574908 (Python Code)

Max Activating Token Index: 711

Text #18

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2694. Min Act: -0.1700

Data Index: 1536829 (Python Code)

Max Activating Token Index: 298

Text #19

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2694. Min Act: -0.1700

Data Index: 1441252 (Python Code)

Max Activating Token Index: 406