Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1264 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.4030. Min Act: -0.1700

Data Index: 57297 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.2618. Min Act: -0.1700

Data Index: 938077 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.2303. Min Act: -0.1700

Data Index: 30675 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.1831. Min Act: -0.1700

Data Index: 1553323 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.1674. Min Act: -0.1700

Data Index: 817475 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.1201. Min Act: -0.1700

Data Index: 1440599 (Python Code)

Max Activating Token Index: 242

Text #6

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.1201. Min Act: -0.1700

Data Index: 1113035 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.1044. Min Act: -0.1700

Data Index: 1397498 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0886. Min Act: -0.1700

Data Index: 772985 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0570. Min Act: -0.1700

Data Index: 1522116 (Python Code)

Max Activating Token Index: 420

Text #10

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0413. Min Act: -0.1700

Data Index: 1565390 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0570. Min Act: -0.1700

Data Index: 1623396 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0413. Min Act: -0.1700

Data Index: 1554824 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0570. Min Act: -0.1700

Data Index: 266114 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0570. Min Act: -0.1700

Data Index: 813747 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0570. Min Act: -0.1700

Data Index: 1426788 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0570. Min Act: -0.1700

Data Index: 1637359 (Python Code)

Max Activating Token Index: 838

Text #17

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0570. Min Act: -0.1700

Data Index: 1655404 (Python Code)

Max Activating Token Index: 775

Text #18

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0413. Min Act: -0.1700

Data Index: 1462667 (Python Code)

Max Activating Token Index: 396

Text #19

Max Range: 3.4030. Min Range: -3.4030

Max Act: 3.0255. Min Act: -0.1700

Data Index: 1170586 (C4 (Web Text))

Max Activating Token Index: 790