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

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

Neuron 5143 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1007443 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0790. Min Act: -0.0000

Data Index: 337188 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1539225 (Python Code)

Max Activating Token Index: 343

Text #3

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0145. Min Act: -0.0000

Data Index: 113940 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1582151 (Python Code)

Max Activating Token Index: 646

Text #5

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1393050 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0144. Min Act: -0.0000

Data Index: 127015 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1448445 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9013. Min Act: -0.0000

Data Index: 545461 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1572720 (Python Code)

Max Activating Token Index: 592

Text #10

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8728. Min Act: -0.0000

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1549907 (Python Code)

Max Activating Token Index: 160

Text #12

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1470728 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1134050 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1483326 (Python Code)

Max Activating Token Index: 631

Text #15

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1655649 (Python Code)

Max Activating Token Index: 679

Text #16

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8052. Min Act: -0.0000

Data Index: 472286 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1378178 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1562757 (Python Code)

Max Activating Token Index: 345

Text #19

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8492. Min Act: -0.0000

Data Index: 940266 (C4 (Web Text))

Max Activating Token Index: 283