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

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

Neuron 3407 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2084. Min Range: -1.2084

Max Act: 1.2084. Min Act: -0.0000

Data Index: 973280 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.9936. Min Act: -0.0000

Data Index: 772718 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.2084. Min Range: -1.2084

Max Act: 1.0126. Min Act: -0.0000

Data Index: 450274 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1050277 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.8859. Min Act: -0.0000

Data Index: 1046907 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.8376. Min Act: -0.0000

Data Index: 310092 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.8256. Min Act: -0.0000

Data Index: 8912 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.8297. Min Act: -0.0000

Data Index: 402591 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1123117 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.7689. Min Act: -0.0000

Data Index: 433542 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.7541. Min Act: -0.0000

Data Index: 837246 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.6850. Min Act: -0.0000

Data Index: 716353 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.7832. Min Act: -0.0000

Data Index: 687954 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.7729. Min Act: -0.0000

Data Index: 745239 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.7475. Min Act: -0.0000

Data Index: 208536 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.7292. Min Act: -0.0000

Data Index: 367244 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.6920. Min Act: -0.0000

Data Index: 126773 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.7053. Min Act: -0.0000

Data Index: 260278 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1463926 (Python Code)

Max Activating Token Index: 720

Text #19

Max Range: 1.2084. Min Range: -1.2084

Max Act: 0.6985. Min Act: -0.0000

Data Index: 995601 (C4 (Web Text))

Max Activating Token Index: 72