Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 410 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.1977. Min Act: -0.0001

Data Index: 1310581 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.1368. Min Act: -0.0000

Data Index: 115641 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.1689. Min Act: -0.0001

Data Index: 397301 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.1346. Min Act: -0.0000

Data Index: 404064 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.1151. Min Act: -0.0001

Data Index: 968791 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.2073. Min Act: -0.0001

Data Index: 653492 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0999. Min Act: -0.0001

Data Index: 356119 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1036993 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0771. Min Act: -0.0001

Data Index: 1243859 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.1317. Min Act: -0.0001

Data Index: 907705 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.1190. Min Act: -0.0001

Data Index: 384015 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0241. Min Act: -0.0001

Data Index: 926478 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0192. Min Act: -0.0001

Data Index: 26384 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0733. Min Act: -0.0001

Data Index: 790376 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0674. Min Act: -0.0001

Data Index: 1224626 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0184. Min Act: -0.0001

Data Index: 777144 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0202. Min Act: -0.0001

Data Index: 440963 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0215. Min Act: -0.0001

Data Index: 412141 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0133. Min Act: -0.0001

Data Index: 670861 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9457. Min Act: -0.0001

Data Index: 768498 (C4 (Web Text))

Max Activating Token Index: 144