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

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

Neuron 1643 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: 0.2984. Min Range: -0.2984

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1018520 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1309402 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2828. Min Act: -0.0000

Data Index: 218232 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2665. Min Act: -0.0000

Data Index: 780271 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2389. Min Act: -0.0000

Data Index: 455397 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2545. Min Act: -0.0000

Data Index: 339543 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2255. Min Act: -0.0000

Data Index: 93834 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1651589 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1216990 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2273. Min Act: -0.0000

Data Index: 404691 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2243. Min Act: -0.0000

Data Index: 675152 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1091534 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1030262 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1027844 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1839. Min Act: -0.0000

Data Index: 712066 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2005. Min Act: -0.0000

Data Index: 568333 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1875. Min Act: -0.0000

Data Index: 45439 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1932. Min Act: -0.0000

Data Index: 618787 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1920. Min Act: -0.0000

Data Index: 608930 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1976. Min Act: -0.0000

Data Index: 739667 (C4 (Web Text))

Max Activating Token Index: 192