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

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

Neuron 3362 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: 0.2361. Min Range: -0.2361

Max Act: 0.2296. Min Act: -0.0000

Data Index: 730356 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2149. Min Act: -0.0000

Data Index: 589313 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2246. Min Act: -0.0000

Data Index: 705558 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2244. Min Act: -0.0000

Data Index: 203943 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1127539 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2193. Min Act: -0.0000

Data Index: 380466 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2169. Min Act: -0.0000

Data Index: 837020 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2089. Min Act: -0.0000

Data Index: 669457 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1239885 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1952. Min Act: -0.0000

Data Index: 915308 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2031. Min Act: -0.0000

Data Index: 425891 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2093. Min Act: -0.0000

Data Index: 231218 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2016. Min Act: -0.0000

Data Index: 387899 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1005858 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1350657 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1687. Min Act: 0.0000

Data Index: 1333047 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1801. Min Act: -0.0000

Data Index: 798506 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1671. Min Act: -0.0000

Data Index: 529796 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1662. Min Act: -0.0000

Data Index: 759753 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1645. Min Act: -0.0000

Data Index: 379496 (C4 (Web Text))

Max Activating Token Index: 243