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

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

Neuron 1911 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: 5.5424. Min Range: -5.5424

Max Act: 5.5424. Min Act: -0.1700

Data Index: 1056467 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.5112. Min Act: -0.1700

Data Index: 1580880 (Python Code)

Max Activating Token Index: 470

Text #2

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.4799. Min Act: -0.1700

Data Index: 991815 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.3862. Min Act: -0.1700

Data Index: 1452027 (Python Code)

Max Activating Token Index: 997

Text #4

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.4487. Min Act: -0.1699

Data Index: 450191 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.3549. Min Act: -0.1700

Data Index: 1494544 (Python Code)

Max Activating Token Index: 1016

Text #6

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.3237. Min Act: -0.1700

Data Index: 1615834 (Python Code)

Max Activating Token Index: 987

Text #7

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.3862. Min Act: -0.1700

Data Index: 1124108 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.3549. Min Act: -0.1700

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.2924. Min Act: -0.1700

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.2924. Min Act: -0.1700

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.2299. Min Act: -0.1700

Data Index: 1559947 (Python Code)

Max Activating Token Index: 800

Text #12

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.2612. Min Act: -0.1700

Data Index: 717047 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.2612. Min Act: -0.1700

Data Index: 962027 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.2924. Min Act: -0.1700

Data Index: 141388 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.1987. Min Act: -0.1700

Data Index: 873794 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.1987. Min Act: -0.1700

Data Index: 1521426 (Python Code)

Max Activating Token Index: 902

Text #17

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.2299. Min Act: -0.1700

Data Index: 1435570 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.2924. Min Act: -0.1700

Data Index: 837565 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 5.5424. Min Range: -5.5424

Max Act: 5.1987. Min Act: -0.1700

Data Index: 883916 (C4 (Web Text))

Max Activating Token Index: 245