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

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

Neuron 553 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: 3.2808. Min Range: -3.2808

Max Act: 3.2808. Min Act: -0.1700

Data Index: 1640214 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.1707. Min Act: -0.1700

Data Index: 696832 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.1077. Min Act: -0.1700

Data Index: 140675 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0919. Min Act: -0.1700

Data Index: 1469780 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0919. Min Act: -0.1700

Data Index: 607610 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0761. Min Act: -0.1700

Data Index: 682290 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0761. Min Act: -0.1700

Data Index: 1033479 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0446. Min Act: -0.1700

Data Index: 1230466 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0288. Min Act: -0.1700

Data Index: 727762 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0446. Min Act: -0.1700

Data Index: 697117 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0288. Min Act: -0.1700

Data Index: 795763 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0288. Min Act: -0.1700

Data Index: 834808 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0288. Min Act: -0.1700

Data Index: 57391 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0288. Min Act: -0.1700

Data Index: 1629967 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0130. Min Act: -0.1700

Data Index: 1068327 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0130. Min Act: -0.1700

Data Index: 11712 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0130. Min Act: -0.1700

Data Index: 650943 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 3.2808. Min Range: -3.2808

Max Act: 3.0130. Min Act: -0.1700

Data Index: 6369 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 3.2808. Min Range: -3.2808

Max Act: 2.9972. Min Act: -0.1700

Data Index: 1257300 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 3.2808. Min Range: -3.2808

Max Act: 2.9972. Min Act: -0.1700

Data Index: 893447 (C4 (Web Text))

Max Activating Token Index: 11