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

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

Neuron 744 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: 3.8083. Min Range: -3.8083

Max Act: 3.8083. Min Act: -0.1699

Data Index: 1457221 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7663. Min Act: -0.1700

Data Index: 74367 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7710. Min Act: -0.1700

Data Index: 437157 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7415. Min Act: -0.1700

Data Index: 1616542 (Python Code)

Max Activating Token Index: 834

Text #4

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6878. Min Act: -0.1700

Data Index: 413561 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6623. Min Act: -0.1685

Data Index: 1506989 (Python Code)

Max Activating Token Index: 789

Text #6

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6687. Min Act: -0.1700

Data Index: 1547323 (Python Code)

Max Activating Token Index: 882

Text #7

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6513. Min Act: -0.1700

Data Index: 300719 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5501. Min Act: -0.1662

Data Index: 1533891 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5446. Min Act: -0.1697

Data Index: 1571987 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5555. Min Act: -0.1700

Data Index: 484667 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5533. Min Act: -0.1700

Data Index: 563405 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5266. Min Act: -0.1669

Data Index: 1490059 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4998. Min Act: -0.1553

Data Index: 1581474 (Python Code)

Max Activating Token Index: 760

Text #14

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4780. Min Act: -0.1700

Data Index: 1455090 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5017. Min Act: -0.1661

Data Index: 1378971 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4551. Min Act: -0.1600

Data Index: 1373534 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4592. Min Act: -0.1699

Data Index: 1430613 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4448. Min Act: -0.1089

Data Index: 1539629 (Python Code)

Max Activating Token Index: 88

Text #19

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4508. Min Act: -0.1696

Data Index: 1208327 (C4 (Web Text))

Max Activating Token Index: 751