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

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

Neuron 833 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.3390. Min Act: -0.0000

Data Index: 258820 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.4047. Min Act: -0.0000

Data Index: 925881 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.3472. Min Act: -0.0000

Data Index: 84098 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.1881. Min Act: -0.0000

Data Index: 1419510 (Python Code)

Max Activating Token Index: 320

Text #4

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.2958. Min Act: -0.0000

Data Index: 1262669 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 3.4047. Min Range: -3.4047

Max Act: 2.7588. Min Act: -0.0000

Data Index: 470815 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.2433. Min Act: -0.0000

Data Index: 292342 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.0470. Min Act: -0.0000

Data Index: 777569 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.0355. Min Act: -0.0000

Data Index: 33268 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 3.4047. Min Range: -3.4047

Max Act: 2.8687. Min Act: -0.0000

Data Index: 947271 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.0332. Min Act: -0.0000

Data Index: 1522127 (Python Code)

Max Activating Token Index: 318

Text #11

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.1004. Min Act: -0.0000

Data Index: 263458 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 3.4047. Min Range: -3.4047

Max Act: 3.1013. Min Act: -0.0000

Data Index: 938156 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 3.4047. Min Range: -3.4047

Max Act: 2.7866. Min Act: -0.0000

Data Index: 1555565 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 3.4047. Min Range: -3.4047

Max Act: 2.8747. Min Act: -0.0000

Data Index: 469976 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 3.4047. Min Range: -3.4047

Max Act: 2.7119. Min Act: -0.0000

Data Index: 387620 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 3.4047. Min Range: -3.4047

Max Act: 2.8146. Min Act: -0.0000

Data Index: 1232829 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 3.4047. Min Range: -3.4047

Max Act: 2.4801. Min Act: -0.0000

Data Index: 541134 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 3.4047. Min Range: -3.4047

Max Act: 2.7565. Min Act: -0.0000

Data Index: 110033 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 3.4047. Min Range: -3.4047

Max Act: 2.7383. Min Act: -0.0000

Data Index: 780725 (C4 (Web Text))

Max Activating Token Index: 50