Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1650 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1621. Min Range: -2.1621

Max Act: 2.1621. Min Act: -0.0000

Data Index: 187336 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.7958. Min Act: -0.0000

Data Index: 1316711 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.8387. Min Act: -0.0000

Data Index: 974960 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.6169. Min Act: -0.0000

Data Index: 36085 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.6851. Min Act: -0.0000

Data Index: 364988 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.6758. Min Act: -0.0000

Data Index: 748086 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.5514. Min Act: -0.0000

Data Index: 296964 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1057000 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.6337. Min Act: -0.0000

Data Index: 339732 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.3904. Min Act: -0.0000

Data Index: 825460 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.4677. Min Act: -0.0000

Data Index: 853876 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.5299. Min Act: -0.0000

Data Index: 330970 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.3274. Min Act: -0.0000

Data Index: 244343 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.4865. Min Act: -0.0000

Data Index: 956223 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.3925. Min Act: -0.0000

Data Index: 62728 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.4470. Min Act: -0.0000

Data Index: 338159 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1030617 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.2433. Min Act: -0.0000

Data Index: 861395 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.2956. Min Act: -0.0000

Data Index: 258196 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 2.1621. Min Range: -2.1621

Max Act: 1.2184. Min Act: -0.0000

Data Index: 798085 (C4 (Web Text))

Max Activating Token Index: 543