Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4532 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.4405. Min Act: -0.0000

Data Index: 26645 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.4001. Min Act: -0.0000

Data Index: 195296 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.3262. Min Act: -0.0000

Data Index: 330264 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.3685. Min Act: -0.0000

Data Index: 207251 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.3989. Min Act: -0.0000

Data Index: 762268 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.3476. Min Act: -0.0000

Data Index: 1329311 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1703. Min Act: -0.0000

Data Index: 212079 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1954. Min Act: -0.0000

Data Index: 391533 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.0840. Min Act: -0.0000

Data Index: 20610 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1609. Min Act: -0.0000

Data Index: 350967 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1697. Min Act: -0.0000

Data Index: 663761 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1241531 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1639283 (Python Code)

Max Activating Token Index: 787

Text #13

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1155. Min Act: -0.0000

Data Index: 811541 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1595. Min Act: -0.0000

Data Index: 251509 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1435195 (Python Code)

Max Activating Token Index: 883

Text #16

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.0778. Min Act: -0.0000

Data Index: 482394 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1517848 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1605300 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 1.4405. Min Range: -1.4405

Max Act: 1.1079. Min Act: -0.0000

Data Index: 925967 (C4 (Web Text))

Max Activating Token Index: 472