Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1320 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.1064. Min Act: -0.1700

Data Index: 674955 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0591. Min Act: -0.1700

Data Index: 711830 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0433. Min Act: -0.1700

Data Index: 1232522 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0433. Min Act: -0.1700

Data Index: 849182 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0275. Min Act: -0.1700

Data Index: 420104 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0433. Min Act: -0.1700

Data Index: 1304719 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9959. Min Act: -0.1700

Data Index: 1099175 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9959. Min Act: -0.1700

Data Index: 1340194 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9959. Min Act: -0.1700

Data Index: 391058 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0117. Min Act: -0.1700

Data Index: 613094 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9959. Min Act: -0.1700

Data Index: 828501 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9959. Min Act: -0.1700

Data Index: 1144707 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9801. Min Act: -0.1700

Data Index: 125330 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9801. Min Act: -0.1700

Data Index: 826568 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9801. Min Act: -0.1700

Data Index: 325380 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9801. Min Act: -0.1700

Data Index: 503386 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9959. Min Act: -0.1700

Data Index: 645897 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9801. Min Act: -0.1700

Data Index: 1006550 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9326. Min Act: -0.1700

Data Index: 663609 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9642. Min Act: -0.1700

Data Index: 575915 (C4 (Web Text))

Max Activating Token Index: 336