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

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

Neuron 236 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.6061. Min Act: -0.1700

Data Index: 1064067 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.4495. Min Act: -0.1700

Data Index: 804620 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.4181. Min Act: -0.1700

Data Index: 73220 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.4181. Min Act: -0.1700

Data Index: 5069 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.4181. Min Act: -0.1700

Data Index: 621812 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3554. Min Act: -0.1700

Data Index: 245057 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3867. Min Act: -0.1700

Data Index: 800134 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3867. Min Act: -0.1700

Data Index: 1169897 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3554. Min Act: -0.1700

Data Index: 200112 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3554. Min Act: -0.1700

Data Index: 492856 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.2926. Min Act: -0.1700

Data Index: 140817 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3867. Min Act: -0.1700

Data Index: 1295263 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3554. Min Act: -0.1700

Data Index: 1153381 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3240. Min Act: -0.1700

Data Index: 639678 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3240. Min Act: -0.1700

Data Index: 340183 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3240. Min Act: -0.1700

Data Index: 1073002 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3240. Min Act: -0.1700

Data Index: 1230004 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3240. Min Act: -0.1700

Data Index: 1238490 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3240. Min Act: -0.1700

Data Index: 348995 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 3.6061. Min Range: -3.6061

Max Act: 3.3554. Min Act: -0.1700

Data Index: 425984 (C4 (Web Text))

Max Activating Token Index: 207