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

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

Neuron 1570 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.6720. Min Act: -0.1700

Data Index: 1636724 (Python Code)

Max Activating Token Index: 648

Text #1

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.6095. Min Act: -0.1700

Data Index: 1580240 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.4220. Min Act: -0.1700

Data Index: 1428933 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.2033. Min Act: -0.1700

Data Index: 1538667 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.1095. Min Act: -0.1700

Data Index: 1581288 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.2970. Min Act: -0.1700

Data Index: 1602945 (Python Code)

Max Activating Token Index: 476

Text #6

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0783. Min Act: -0.1700

Data Index: 1541334 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.1408. Min Act: -0.1700

Data Index: 1368728 (Python Code)

Max Activating Token Index: 542

Text #8

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0783. Min Act: -0.1700

Data Index: 1516153 (Python Code)

Max Activating Token Index: 406

Text #9

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0783. Min Act: -0.1700

Data Index: 1422114 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0158. Min Act: -0.1700

Data Index: 1480502 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0470. Min Act: -0.1700

Data Index: 1543512 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0158. Min Act: -0.1700

Data Index: 1514595 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 5.6720. Min Range: -5.6720

Max Act: 4.9845. Min Act: -0.1700

Data Index: 1628777 (Python Code)

Max Activating Token Index: 184

Text #14

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0783. Min Act: -0.1698

Data Index: 1566625 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 5.6720. Min Range: -5.6720

Max Act: 4.9845. Min Act: -0.1700

Data Index: 1431688 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 5.6720. Min Range: -5.6720

Max Act: 4.9220. Min Act: -0.1700

Data Index: 1418703 (Python Code)

Max Activating Token Index: 717

Text #17

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0470. Min Act: -0.1699

Data Index: 1478924 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0470. Min Act: -0.1699

Data Index: 1458708 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 5.6720. Min Range: -5.6720

Max Act: 5.0783. Min Act: -0.1700

Data Index: 1530681 (Python Code)

Max Activating Token Index: 1023