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

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

Neuron 6105 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.5952. Min Act: -0.0001

Data Index: 303442 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1199264 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4113. Min Act: -0.0001

Data Index: 171159 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4641. Min Act: -0.0001

Data Index: 1276974 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2797. Min Act: -0.0001

Data Index: 244850 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2529. Min Act: -0.0001

Data Index: 686920 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2042. Min Act: -0.0001

Data Index: 1345252 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.1022. Min Act: -0.0001

Data Index: 465691 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2286. Min Act: -0.0001

Data Index: 1145259 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.0818. Min Act: -0.0001

Data Index: 518929 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.0751. Min Act: -0.0001

Data Index: 618307 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.0247. Min Act: -0.0001

Data Index: 422181 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.0844. Min Act: -0.0001

Data Index: 551112 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.1034. Min Act: -0.0001

Data Index: 1100239 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 1.5952. Min Range: -1.5952

Max Act: 0.9787. Min Act: -0.0001

Data Index: 7321 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 1.5952. Min Range: -1.5952

Max Act: 0.9895. Min Act: -0.0001

Data Index: 391870 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.1067. Min Act: -0.0001

Data Index: 226181 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 1.5952. Min Range: -1.5952

Max Act: 0.9118. Min Act: -0.0001

Data Index: 20749 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 1.5952. Min Range: -1.5952

Max Act: 0.9738. Min Act: -0.0001

Data Index: 464204 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.5952. Min Range: -1.5952

Max Act: 0.9618. Min Act: -0.0001

Data Index: 556767 (C4 (Web Text))

Max Activating Token Index: 129