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

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

Neuron 1671 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2832. Min Act: -0.1699

Data Index: 1244088 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2207. Min Act: -0.1700

Data Index: 7520 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2520. Min Act: -0.1700

Data Index: 808809 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2520. Min Act: -0.1700

Data Index: 886105 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.1895. Min Act: -0.1700

Data Index: 741999 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2832. Min Act: -0.1700

Data Index: 1149159 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2207. Min Act: -0.1700

Data Index: 726885 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2520. Min Act: -0.1700

Data Index: 795953 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2207. Min Act: -0.1700

Data Index: 45038 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2207. Min Act: -0.1700

Data Index: 1036267 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2520. Min Act: -0.1700

Data Index: 982200 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2207. Min Act: -0.1700

Data Index: 954932 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.1895. Min Act: -0.1700

Data Index: 592975 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.1582. Min Act: -0.1700

Data Index: 537559 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.2207. Min Act: -0.1700

Data Index: 180324 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.1895. Min Act: -0.1700

Data Index: 786555 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.1582. Min Act: -0.1700

Data Index: 196199 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.1582. Min Act: -0.1700

Data Index: 872057 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.1270. Min Act: -0.1700

Data Index: 1156442 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 5.2832. Min Range: -5.2832

Max Act: 5.1582. Min Act: -0.1700

Data Index: 456419 (C4 (Web Text))

Max Activating Token Index: 245