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

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

Neuron 1903 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.6927. Min Act: -0.1700

Data Index: 1165533 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.5052. Min Act: -0.1700

Data Index: 1167860 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.4427. Min Act: -0.1700

Data Index: 1340156 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.3489. Min Act: -0.1700

Data Index: 124693 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.2864. Min Act: -0.1700

Data Index: 126289 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.2239. Min Act: -0.1700

Data Index: 1222197 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1927. Min Act: -0.1700

Data Index: 239355 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.2239. Min Act: -0.1700

Data Index: 1021904 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1614. Min Act: -0.1700

Data Index: 1256792 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1614. Min Act: -0.1700

Data Index: 341390 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1927. Min Act: -0.1700

Data Index: 1160436 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1927. Min Act: -0.1700

Data Index: 1249254 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1614. Min Act: -0.1700

Data Index: 455418 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1927. Min Act: -0.1700

Data Index: 1307026 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1927. Min Act: -0.1700

Data Index: 1083009 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1614. Min Act: -0.1700

Data Index: 187517 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1302. Min Act: -0.1700

Data Index: 231454 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1614. Min Act: -0.1700

Data Index: 247268 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.1302. Min Act: -0.1700

Data Index: 20962 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 5.6927. Min Range: -5.6927

Max Act: 5.0989. Min Act: -0.1700

Data Index: 104302 (C4 (Web Text))

Max Activating Token Index: 855