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

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

Neuron 1162 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: 3.2038. Min Range: -3.2038

Max Act: 3.2038. Min Act: -0.1700

Data Index: 1117699 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.1724. Min Act: -0.1700

Data Index: 666623 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.1093. Min Act: -0.1700

Data Index: 648709 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0620. Min Act: -0.1700

Data Index: 825452 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0305. Min Act: -0.1700

Data Index: 1160126 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0462. Min Act: -0.1700

Data Index: 52616 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0462. Min Act: -0.1700

Data Index: 873087 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0305. Min Act: -0.1700

Data Index: 691995 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 3.2038. Min Range: -3.2038

Max Act: 2.9988. Min Act: -0.1700

Data Index: 205753 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0147. Min Act: -0.1700

Data Index: 1318276 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0147. Min Act: -0.1700

Data Index: 134198 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0147. Min Act: -0.1700

Data Index: 411306 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0305. Min Act: -0.1700

Data Index: 374678 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 3.2038. Min Range: -3.2038

Max Act: 2.9830. Min Act: -0.1700

Data Index: 1074960 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 3.2038. Min Range: -3.2038

Max Act: 2.9988. Min Act: -0.1700

Data Index: 802518 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 3.2038. Min Range: -3.2038

Max Act: 3.0147. Min Act: -0.1700

Data Index: 1105081 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 3.2038. Min Range: -3.2038

Max Act: 2.9988. Min Act: -0.1700

Data Index: 763855 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 3.2038. Min Range: -3.2038

Max Act: 2.9672. Min Act: -0.1700

Data Index: 592539 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 3.2038. Min Range: -3.2038

Max Act: 2.9672. Min Act: -0.1700

Data Index: 318836 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 3.2038. Min Range: -3.2038

Max Act: 2.9830. Min Act: -0.1700

Data Index: 1085410 (C4 (Web Text))

Max Activating Token Index: 473