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

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

Neuron 2230 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8461. Min Range: -6.8461

Max Act: 6.8461. Min Act: -0.0000

Data Index: 316998 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 6.8461. Min Range: -6.8461

Max Act: 6.1800. Min Act: -0.0000

Data Index: 206146 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 6.8461. Min Range: -6.8461

Max Act: 5.0291. Min Act: -0.0001

Data Index: 410298 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.7920. Min Act: -0.0000

Data Index: 102627 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 6.8461. Min Range: -6.8461

Max Act: 5.2287. Min Act: -0.0001

Data Index: 1176906 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.4530. Min Act: -0.0000

Data Index: 1280920 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.6657. Min Act: -0.0001

Data Index: 371949 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.3295. Min Act: -0.0000

Data Index: 537774 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.2857. Min Act: -0.0000

Data Index: 296647 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.5155. Min Act: -0.0000

Data Index: 566683 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.1350. Min Act: -0.0000

Data Index: 1294626 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.2570. Min Act: -0.0000

Data Index: 853981 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.2652. Min Act: -0.0001

Data Index: 337989 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.1213. Min Act: -0.0000

Data Index: 239845 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.1707. Min Act: -0.0000

Data Index: 103384 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 6.8461. Min Range: -6.8461

Max Act: 3.9430. Min Act: -0.0001

Data Index: 1250899 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.1265. Min Act: -0.0001

Data Index: 284650 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 6.8461. Min Range: -6.8461

Max Act: 3.9953. Min Act: -0.0001

Data Index: 1319837 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.2847. Min Act: -0.0000

Data Index: 841149 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 6.8461. Min Range: -6.8461

Max Act: 4.2539. Min Act: -0.0000

Data Index: 1105162 (C4 (Web Text))

Max Activating Token Index: 917