Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 960 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.8083. Min Act: -0.1700

Data Index: 1509092 (Python Code)

Max Activating Token Index: 873

Text #1

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7770. Min Act: -0.1700

Data Index: 1619022 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7458. Min Act: -0.1700

Data Index: 1472653 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7145. Min Act: -0.1700

Data Index: 1414630 (Python Code)

Max Activating Token Index: 714

Text #4

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7145. Min Act: -0.1700

Data Index: 1496690 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7301. Min Act: -0.1700

Data Index: 1535253 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7458. Min Act: -0.1700

Data Index: 1510781 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7145. Min Act: -0.1700

Data Index: 1476937 (Python Code)

Max Activating Token Index: 380

Text #8

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7458. Min Act: -0.1700

Data Index: 1437333 (Python Code)

Max Activating Token Index: 915

Text #9

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7301. Min Act: -0.1700

Data Index: 1541139 (Python Code)

Max Activating Token Index: 283

Text #10

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7145. Min Act: -0.1700

Data Index: 1460361 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7145. Min Act: -0.1700

Data Index: 1570862 (Python Code)

Max Activating Token Index: 802

Text #12

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6832. Min Act: -0.1700

Data Index: 1412061 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6832. Min Act: -0.1700

Data Index: 1421590 (Python Code)

Max Activating Token Index: 485

Text #14

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6519. Min Act: -0.1700

Data Index: 1565897 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7301. Min Act: -0.1700

Data Index: 1497916 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6049. Min Act: -0.1700

Data Index: 1593791 (Python Code)

Max Activating Token Index: 835

Text #17

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7145. Min Act: -0.1700

Data Index: 1578188 (Python Code)

Max Activating Token Index: 851

Text #18

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6988. Min Act: -0.1700

Data Index: 1567218 (Python Code)

Max Activating Token Index: 171

Text #19

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6832. Min Act: -0.1700

Data Index: 1566227 (Python Code)

Max Activating Token Index: 755