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

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

Neuron 3051 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.8609. Min Act: -0.0000

Data Index: 258076 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.6917. Min Act: -0.0000

Data Index: 403435 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5573. Min Act: -0.0000

Data Index: 1045905 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.6456. Min Act: -0.0000

Data Index: 21889 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5327. Min Act: -0.0000

Data Index: 997717 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.6069. Min Act: -0.0000

Data Index: 829694 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5095. Min Act: -0.0000

Data Index: 1072065 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3615. Min Act: -0.0000

Data Index: 952311 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3599. Min Act: -0.0000

Data Index: 900245 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.4104. Min Act: -0.0000

Data Index: 69543 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3948. Min Act: -0.0000

Data Index: 443481 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3597. Min Act: -0.0000

Data Index: 1319476 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3110. Min Act: -0.0000

Data Index: 13020 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.2941. Min Act: -0.0000

Data Index: 785258 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.1538. Min Act: -0.0000

Data Index: 291068 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3026. Min Act: -0.0000

Data Index: 444348 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.2908. Min Act: -0.0000

Data Index: 1084309 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3590. Min Act: -0.0000

Data Index: 829993 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1202765 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1146726 (C4 (Web Text))

Max Activating Token Index: 425