Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4302 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1402726 (Python Code)

Max Activating Token Index: 389

Text #1

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1445231 (Python Code)

Max Activating Token Index: 124

Text #2

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.4483. Min Act: -0.0001

Data Index: 1530543 (Python Code)

Max Activating Token Index: 540

Text #3

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3887. Min Act: -0.0000

Data Index: 1554783 (Python Code)

Max Activating Token Index: 575

Text #4

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.5098. Min Act: -0.0001

Data Index: 1603538 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1533787 (Python Code)

Max Activating Token Index: 735

Text #6

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3712. Min Act: -0.0001

Data Index: 1563890 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3157. Min Act: -0.0001

Data Index: 1621638 (Python Code)

Max Activating Token Index: 861

Text #8

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1361942 (Python Code)

Max Activating Token Index: 502

Text #9

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3305. Min Act: -0.0001

Data Index: 1484354 (Python Code)

Max Activating Token Index: 983

Text #10

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3134. Min Act: -0.0000

Data Index: 1537495 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3144. Min Act: -0.0000

Data Index: 1463901 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3443. Min Act: -0.0001

Data Index: 1547961 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3313. Min Act: -0.0000

Data Index: 1360684 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.2890. Min Act: -0.0001

Data Index: 1363170 (Python Code)

Max Activating Token Index: 323

Text #15

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.2530. Min Act: -0.0001

Data Index: 1485343 (Python Code)

Max Activating Token Index: 866

Text #16

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3209. Min Act: -0.0001

Data Index: 1604466 (Python Code)

Max Activating Token Index: 699

Text #17

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3206. Min Act: -0.0001

Data Index: 1391060 (Python Code)

Max Activating Token Index: 143

Text #18

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.2875. Min Act: -0.0001

Data Index: 1624353 (Python Code)

Max Activating Token Index: 339

Text #19

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3675. Min Act: -0.0001

Data Index: 1399728 (Python Code)

Max Activating Token Index: 60