Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1388 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0960. Min Act: -0.0006

Data Index: 627342 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0941. Min Act: -0.0006

Data Index: 814761 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0924. Min Act: -0.0006

Data Index: 828471 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0763. Min Act: -0.0006

Data Index: 1274640 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0630. Min Act: -0.0006

Data Index: 860950 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0823. Min Act: -0.0006

Data Index: 320065 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0743. Min Act: -0.0006

Data Index: 1138322 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0770. Min Act: -0.0006

Data Index: 152722 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0725. Min Act: -0.0006

Data Index: 193669 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0795. Min Act: -0.0006

Data Index: 382282 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0659. Min Act: -0.0006

Data Index: 58517 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0657. Min Act: -0.0006

Data Index: 1096480 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0783. Min Act: -0.0006

Data Index: 674299 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0780. Min Act: -0.0006

Data Index: 1076546 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0608. Min Act: -0.0006

Data Index: 30797 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0653. Min Act: -0.0006

Data Index: 502711 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0749. Min Act: -0.0006

Data Index: 880809 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0590. Min Act: -0.0006

Data Index: 762945 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0706. Min Act: -0.0006

Data Index: 1037009 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0794. Min Act: -0.0006

Data Index: 636687 (C4 (Web Text))

Max Activating Token Index: 735