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

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

Neuron 6103 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1729. Min Range: -2.1729

Max Act: 2.1729. Min Act: -0.0000

Data Index: 461031 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 2.1729. Min Range: -2.1729

Max Act: 1.8599. Min Act: -0.0000

Data Index: 634191 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 2.1729. Min Range: -2.1729

Max Act: 2.0192. Min Act: -0.0000

Data Index: 206039 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 2.1729. Min Range: -2.1729

Max Act: 1.7836. Min Act: -0.0000

Data Index: 632835 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 2.1729. Min Range: -2.1729

Max Act: 2.0057. Min Act: -0.0000

Data Index: 1229511 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 2.1729. Min Range: -2.1729

Max Act: 1.9928. Min Act: -0.0000

Data Index: 828319 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 2.1729. Min Range: -2.1729

Max Act: 1.7675. Min Act: -0.0000

Data Index: 392166 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 2.1729. Min Range: -2.1729

Max Act: 1.6790. Min Act: -0.0000

Data Index: 569512 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 2.1729. Min Range: -2.1729

Max Act: 1.6574. Min Act: -0.0000

Data Index: 664997 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 2.1729. Min Range: -2.1729

Max Act: 1.1446. Min Act: -0.0000

Data Index: 1347931 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.9593. Min Act: -0.0000

Data Index: 170962 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.9171. Min Act: 0.0000

Data Index: 243202 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.9419. Min Act: -0.0000

Data Index: 810407 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.8576. Min Act: -0.0000

Data Index: 470585 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.8431. Min Act: -0.0000

Data Index: 363520 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1191509 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.8259. Min Act: -0.0000

Data Index: 70672 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1122353 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.7967. Min Act: -0.0000

Data Index: 742633 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 2.1729. Min Range: -2.1729

Max Act: 0.7405. Min Act: -0.0000

Data Index: 425402 (C4 (Web Text))

Max Activating Token Index: 668