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

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

Neuron 1340 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: 1.9916. Min Range: -1.9916

Max Act: 1.9916. Min Act: -0.0001

Data Index: 1150898 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.6416. Min Act: -0.0001

Data Index: 468975 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.3906. Min Act: -0.0001

Data Index: 490511 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.3270. Min Act: -0.0001

Data Index: 593354 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1949. Min Act: -0.0001

Data Index: 19472 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.3034. Min Act: -0.0001

Data Index: 928939 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.2245. Min Act: -0.0001

Data Index: 272317 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.2425. Min Act: -0.0001

Data Index: 862890 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.2372. Min Act: -0.0000

Data Index: 395305 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1832. Min Act: -0.0000

Data Index: 325093 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.2126. Min Act: -0.0001

Data Index: 948757 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1746. Min Act: -0.0000

Data Index: 980188 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1547. Min Act: -0.0001

Data Index: 993555 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.2447. Min Act: -0.0001

Data Index: 1240049 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1602. Min Act: -0.0001

Data Index: 1358841 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.2325. Min Act: -0.0001

Data Index: 35050 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1911. Min Act: -0.0001

Data Index: 959333 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1863. Min Act: -0.0001

Data Index: 1284925 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1212. Min Act: -0.0001

Data Index: 720424 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.9916. Min Range: -1.9916

Max Act: 1.1739. Min Act: -0.0001

Data Index: 153695 (C4 (Web Text))

Max Activating Token Index: 68