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

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

Neuron 95 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1048375 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.2167. Min Act: -0.0001

Data Index: 328798 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.2230. Min Act: -0.0001

Data Index: 342713 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.2149. Min Act: -0.0001

Data Index: 149959 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.2137. Min Act: -0.0000

Data Index: 159833 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.2121. Min Act: -0.0000

Data Index: 368946 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1341406 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1018565 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.2045. Min Act: -0.0001

Data Index: 474403 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1977. Min Act: -0.0001

Data Index: 444439 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1995. Min Act: -0.0001

Data Index: 682752 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1112826 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1280676 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1878. Min Act: -0.0000

Data Index: 858373 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1869. Min Act: -0.0000

Data Index: 703170 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1893. Min Act: -0.0000

Data Index: 59370 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1822. Min Act: -0.0000

Data Index: 555602 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1811. Min Act: -0.0000

Data Index: 767534 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1863. Min Act: -0.0000

Data Index: 777174 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.2388. Min Range: -0.2388

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1182630 (C4 (Web Text))

Max Activating Token Index: 884