Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1116 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.6582. Min Act: -0.0001

Data Index: 780247 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.6068. Min Act: -0.0001

Data Index: 789019 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5511. Min Act: -0.0001

Data Index: 248623 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5635. Min Act: -0.0001

Data Index: 765841 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5518. Min Act: -0.0001

Data Index: 808401 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5458. Min Act: -0.0001

Data Index: 454253 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5447. Min Act: -0.0001

Data Index: 1169225 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5331. Min Act: -0.0001

Data Index: 1250956 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5255. Min Act: -0.0001

Data Index: 1215141 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5293. Min Act: -0.0001

Data Index: 272216 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5281. Min Act: -0.0001

Data Index: 177218 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5065. Min Act: -0.0001

Data Index: 276490 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5002. Min Act: -0.0001

Data Index: 422149 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5147. Min Act: -0.0001

Data Index: 803221 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5101. Min Act: -0.0001

Data Index: 412143 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5269. Min Act: -0.0001

Data Index: 1155123 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.4930. Min Act: -0.0001

Data Index: 303306 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.4900. Min Act: -0.0001

Data Index: 553839 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5202. Min Act: -0.0001

Data Index: 97842 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.6582. Min Range: -0.6582

Max Act: 0.5201. Min Act: -0.0001

Data Index: 14950 (C4 (Web Text))

Max Activating Token Index: 53