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

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

Neuron 558 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0540. Min Range: -3.0540

Max Act: 3.0540. Min Act: -0.0000

Data Index: 520938 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.5284. Min Act: 0.0001

Data Index: 838167 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.5600. Min Act: -0.0000

Data Index: 164303 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.5462. Min Act: -0.0000

Data Index: 1338051 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.5833. Min Act: -0.0000

Data Index: 818597 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.4271. Min Act: -0.0000

Data Index: 600312 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.5422. Min Act: 0.0000

Data Index: 61616 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.2226. Min Act: -0.0000

Data Index: 185072 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.3213. Min Act: -0.0000

Data Index: 569153 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.3269. Min Act: -0.0000

Data Index: 1210570 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.3075. Min Act: -0.0000

Data Index: 1251152 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.2946. Min Act: -0.0000

Data Index: 666049 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.4092. Min Act: -0.0000

Data Index: 778597 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.3842. Min Act: -0.0000

Data Index: 103248 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.2498. Min Act: -0.0000

Data Index: 1257222 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.2179. Min Act: -0.0000

Data Index: 492567 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.1902. Min Act: 0.0000

Data Index: 1038175 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.1595. Min Act: -0.0000

Data Index: 127163 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.0883. Min Act: -0.0000

Data Index: 763148 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 3.0540. Min Range: -3.0540

Max Act: 2.0966. Min Act: -0.0000

Data Index: 863693 (C4 (Web Text))

Max Activating Token Index: 833