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

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

Neuron 4709 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.1313. Min Range: -10.1313

Max Act: 8.7847. Min Act: 0.0000

Data Index: 285047 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 10.1313. Min Range: -10.1313

Max Act: 8.4901. Min Act: -0.0000

Data Index: 1089724 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 10.1313. Min Range: -10.1313

Max Act: 10.1313. Min Act: -0.0000

Data Index: 585055 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 10.1313. Min Range: -10.1313

Max Act: 9.0873. Min Act: -0.0000

Data Index: 259619 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 10.1313. Min Range: -10.1313

Max Act: 8.3648. Min Act: -0.0000

Data Index: 1303736 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.0092. Min Act: -0.0000

Data Index: 115670 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.4299. Min Act: -0.0000

Data Index: 595278 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.0440. Min Act: -0.0000

Data Index: 934127 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.3998. Min Act: -0.0000

Data Index: 620717 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1135155 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1048540 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 10.1313. Min Range: -10.1313

Max Act: 5.4403. Min Act: -0.0000

Data Index: 942457 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1514792 (Python Code)

Max Activating Token Index: 363

Text #13

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1327527 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.1968. Min Act: -0.0000

Data Index: 606502 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.1894. Min Act: -0.0000

Data Index: 974179 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1357096 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.1888. Min Act: -0.0000

Data Index: 353582 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.1670. Min Act: -0.0000

Data Index: 82166 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 10.1313. Min Range: -10.1313

Max Act: 0.1973. Min Act: -0.0000

Data Index: 829191 (C4 (Web Text))

Max Activating Token Index: 741