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

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

Neuron 1285 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: 3.9256. Min Range: -3.9256

Max Act: 3.9256. Min Act: -0.1700

Data Index: 8765 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.8819. Min Act: -0.1700

Data Index: 1359718 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.8535. Min Act: -0.1700

Data Index: 1187904 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.8583. Min Act: -0.1613

Data Index: 372205 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.7475. Min Act: -0.1700

Data Index: 1586877 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.7472. Min Act: -0.1699

Data Index: 184800 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.7567. Min Act: -0.1700

Data Index: 460726 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.6799. Min Act: -0.1699

Data Index: 189446 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.7126. Min Act: -0.1699

Data Index: 1531385 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.6944. Min Act: -0.1690

Data Index: 1592869 (Python Code)

Max Activating Token Index: 439

Text #10

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.6555. Min Act: -0.1444

Data Index: 1503968 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.5310. Min Act: -0.1700

Data Index: 848370 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.5536. Min Act: -0.1700

Data Index: 1335559 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.4893. Min Act: -0.1699

Data Index: 1254011 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.5086. Min Act: -0.1695

Data Index: 1422178 (Python Code)

Max Activating Token Index: 194

Text #15

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.5173. Min Act: -0.1632

Data Index: 1518558 (Python Code)

Max Activating Token Index: 215

Text #16

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.5010. Min Act: -0.1698

Data Index: 1615104 (Python Code)

Max Activating Token Index: 595

Text #17

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.5182. Min Act: -0.1554

Data Index: 1057585 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.4999. Min Act: -0.1444

Data Index: 1479861 (Python Code)

Max Activating Token Index: 264

Text #19

Max Range: 3.9256. Min Range: -3.9256

Max Act: 3.4881. Min Act: -0.1700

Data Index: 239238 (C4 (Web Text))

Max Activating Token Index: 433