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

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

Neuron 1312 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0922. Min Range: -3.0922

Max Act: 3.0922. Min Act: -0.1700

Data Index: 520288 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.9658. Min Act: -0.1700

Data Index: 109895 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.9342. Min Act: -0.1700

Data Index: 974104 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.9183. Min Act: -0.1700

Data Index: 1025174 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.9183. Min Act: -0.1700

Data Index: 55812 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.9025. Min Act: -0.1700

Data Index: 614574 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8866. Min Act: -0.1700

Data Index: 795599 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8866. Min Act: -0.1700

Data Index: 661559 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.9025. Min Act: -0.1700

Data Index: 1323939 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8866. Min Act: -0.1700

Data Index: 1010640 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8707. Min Act: -0.1700

Data Index: 40074 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8707. Min Act: -0.1700

Data Index: 85796 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8707. Min Act: -0.1700

Data Index: 196337 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8707. Min Act: -0.1700

Data Index: 61430 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8549. Min Act: -0.1700

Data Index: 1143211 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8549. Min Act: -0.1700

Data Index: 134332 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8549. Min Act: -0.1700

Data Index: 348417 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8549. Min Act: -0.1700

Data Index: 1123033 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8549. Min Act: -0.1700

Data Index: 506413 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 3.0922. Min Range: -3.0922

Max Act: 2.8390. Min Act: -0.1700

Data Index: 1121203 (C4 (Web Text))

Max Activating Token Index: 865