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

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

Neuron 2796 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: 0.5664. Min Range: -0.5664

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1116335 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4889. Min Act: 0.0000

Data Index: 468326 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4675. Min Act: 0.0000

Data Index: 274204 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1088856 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4189. Min Act: -0.0000

Data Index: 758156 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4259. Min Act: 0.0000

Data Index: 1002029 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4240. Min Act: 0.0000

Data Index: 1340702 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1427155 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1606816 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4113. Min Act: 0.0000

Data Index: 1525487 (Python Code)

Max Activating Token Index: 811

Text #10

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1500514 (Python Code)

Max Activating Token Index: 966

Text #11

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1235403 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3924. Min Act: -0.0000

Data Index: 110534 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1464433 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1003731 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1602676 (Python Code)

Max Activating Token Index: 824

Text #16

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1463222 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1566968 (Python Code)

Max Activating Token Index: 758

Text #18

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1629339 (Python Code)

Max Activating Token Index: 193

Text #19

Max Range: 0.5664. Min Range: -0.5664

Max Act: 0.3886. Min Act: -0.0000

Data Index: 348847 (C4 (Web Text))

Max Activating Token Index: 648