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

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

Neuron 509 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: 5.0976. Min Range: -5.0976

Max Act: 5.0976. Min Act: -0.0000

Data Index: 23728 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 5.0976. Min Range: -5.0976

Max Act: 4.4864. Min Act: -0.0000

Data Index: 1581284 (Python Code)

Max Activating Token Index: 392

Text #2

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.9645. Min Act: -0.0000

Data Index: 1630607 (Python Code)

Max Activating Token Index: 917

Text #3

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.5802. Min Act: -0.0000

Data Index: 1520936 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.8830. Min Act: -0.0000

Data Index: 1511777 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.9941. Min Act: -0.0000

Data Index: 1221867 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.7386. Min Act: -0.0000

Data Index: 1259750 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 5.0976. Min Range: -5.0976

Max Act: 4.0522. Min Act: -0.0001

Data Index: 1003016 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.5374. Min Act: -0.0000

Data Index: 1541887 (Python Code)

Max Activating Token Index: 809

Text #9

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.4252. Min Act: -0.0000

Data Index: 781626 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.2742. Min Act: -0.0000

Data Index: 901042 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.8770. Min Act: -0.0000

Data Index: 1481268 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.6909. Min Act: -0.0000

Data Index: 1516125 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.5194. Min Act: -0.0000

Data Index: 1327575 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 5.0976. Min Range: -5.0976

Max Act: 2.8739. Min Act: -0.0000

Data Index: 65846 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.7331. Min Act: -0.0000

Data Index: 1451658 (Python Code)

Max Activating Token Index: 205

Text #16

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.4095. Min Act: -0.0000

Data Index: 1462954 (Python Code)

Max Activating Token Index: 730

Text #17

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.2564. Min Act: -0.0001

Data Index: 481009 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.3846. Min Act: -0.0000

Data Index: 673875 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 5.0976. Min Range: -5.0976

Max Act: 3.0820. Min Act: -0.0001

Data Index: 1321361 (C4 (Web Text))

Max Activating Token Index: 271