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

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

Neuron 1039 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: 3.0424. Min Range: -3.0424

Max Act: 3.0424. Min Act: -0.1685

Data Index: 1014306 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.8701. Min Act: -0.1700

Data Index: 847159 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.8569. Min Act: -0.1698

Data Index: 1168243 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.7994. Min Act: -0.1672

Data Index: 1612882 (Python Code)

Max Activating Token Index: 921

Text #4

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.8063. Min Act: -0.1699

Data Index: 1560295 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.7283. Min Act: -0.1598

Data Index: 75958 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.7517. Min Act: -0.1699

Data Index: 728907 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.7336. Min Act: -0.1699

Data Index: 1121141 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.7071. Min Act: -0.1700

Data Index: 761802 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.7113. Min Act: -0.1700

Data Index: 1314222 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.6888. Min Act: -0.1670

Data Index: 1342825 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.7001. Min Act: -0.1700

Data Index: 975730 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.7031. Min Act: -0.1695

Data Index: 13859 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.6820. Min Act: -0.1699

Data Index: 731807 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.6817. Min Act: -0.1700

Data Index: 1302626 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.6945. Min Act: -0.1700

Data Index: 131735 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.6740. Min Act: -0.1698

Data Index: 164686 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.6632. Min Act: -0.1698

Data Index: 976985 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.6723. Min Act: -0.1699

Data Index: 243522 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 3.0424. Min Range: -3.0424

Max Act: 2.6750. Min Act: -0.1698

Data Index: 353672 (C4 (Web Text))

Max Activating Token Index: 118