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

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

Neuron 856 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: 4.0806. Min Range: -4.0806

Max Act: 4.0806. Min Act: -0.1700

Data Index: 1286012 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.7679. Min Act: -0.1700

Data Index: 1063063 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.7679. Min Act: -0.1700

Data Index: 739424 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.7992. Min Act: -0.1700

Data Index: 519016 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.7366. Min Act: -0.1700

Data Index: 10037 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6740. Min Act: -0.1700

Data Index: 674897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.7053. Min Act: -0.1700

Data Index: 423471 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6740. Min Act: -0.1700

Data Index: 670708 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6427. Min Act: -0.1700

Data Index: 1109458 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6427. Min Act: -0.1700

Data Index: 1016067 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6114. Min Act: -0.1700

Data Index: 1336892 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6427. Min Act: -0.1700

Data Index: 946826 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6427. Min Act: -0.1700

Data Index: 647052 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6740. Min Act: -0.1700

Data Index: 562255 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6740. Min Act: -0.1700

Data Index: 360119 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1014101 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6114. Min Act: -0.1700

Data Index: 126036 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6114. Min Act: -0.1700

Data Index: 523654 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6114. Min Act: -0.1700

Data Index: 451114 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 4.0806. Min Range: -4.0806

Max Act: 3.6114. Min Act: -0.1700

Data Index: 971253 (C4 (Web Text))

Max Activating Token Index: 841