Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 722 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1980. Min Range: -3.1980

Max Act: 3.1980. Min Act: -0.1700

Data Index: 625270 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 3.1980. Min Range: -3.1980

Max Act: 3.0878. Min Act: -0.1700

Data Index: 781498 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 3.1980. Min Range: -3.1980

Max Act: 3.0246. Min Act: -0.1700

Data Index: 1020528 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.9930. Min Act: -0.1700

Data Index: 7217 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.9930. Min Act: -0.1700

Data Index: 338871 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.9772. Min Act: -0.1700

Data Index: 89675 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.9614. Min Act: -0.1700

Data Index: 1029427 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.9297. Min Act: -0.1700

Data Index: 703870 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.9297. Min Act: -0.1700

Data Index: 1086476 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.9139. Min Act: -0.1700

Data Index: 274931 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.9139. Min Act: -0.1700

Data Index: 1169442 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8980. Min Act: -0.1700

Data Index: 963097 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8980. Min Act: -0.1700

Data Index: 1643715 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8980. Min Act: -0.1700

Data Index: 445296 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8821. Min Act: -0.1700

Data Index: 766992 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8821. Min Act: -0.1700

Data Index: 1520730 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8821. Min Act: -0.1700

Data Index: 1540109 (Python Code)

Max Activating Token Index: 673

Text #17

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8821. Min Act: -0.1700

Data Index: 261435 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8821. Min Act: -0.1700

Data Index: 1473717 (Python Code)

Max Activating Token Index: 670

Text #19

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8663. Min Act: -0.1700

Data Index: 1546991 (Python Code)

Max Activating Token Index: 812