Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 257 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.4630. Min Act: -0.1700

Data Index: 1297119 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.4317. Min Act: -0.1700

Data Index: 159730 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.3689. Min Act: -0.1700

Data Index: 705931 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.3689. Min Act: -0.1700

Data Index: 100548 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.3532. Min Act: -0.1700

Data Index: 142138 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.3376. Min Act: -0.1700

Data Index: 386151 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.3061. Min Act: -0.1700

Data Index: 500255 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.3219. Min Act: -0.1700

Data Index: 663816 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.3219. Min Act: -0.1700

Data Index: 1282938 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.3061. Min Act: -0.1700

Data Index: 907962 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.3061. Min Act: -0.1700

Data Index: 1065853 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.2904. Min Act: -0.1700

Data Index: 1116270 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.2747. Min Act: -0.1700

Data Index: 1219636 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.2904. Min Act: -0.1700

Data Index: 655122 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.2747. Min Act: -0.1700

Data Index: 315905 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.2747. Min Act: -0.1700

Data Index: 797071 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.2590. Min Act: -0.1700

Data Index: 968238 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.2590. Min Act: -0.1700

Data Index: 335017 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.2747. Min Act: -0.1700

Data Index: 943252 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 3.4630. Min Range: -3.4630

Max Act: 3.2590. Min Act: -0.1700

Data Index: 420250 (C4 (Web Text))

Max Activating Token Index: 202