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

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

Neuron 890 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.3327. Min Act: -0.0002

Data Index: 432709 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.3255. Min Act: -0.0002

Data Index: 195531 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.3116. Min Act: -0.0002

Data Index: 390857 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.3081. Min Act: -0.0002

Data Index: 1143606 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2829. Min Act: -0.0003

Data Index: 1302094 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2948. Min Act: -0.0002

Data Index: 853606 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2916. Min Act: -0.0002

Data Index: 1149529 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2959. Min Act: -0.0002

Data Index: 116208 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.3060. Min Act: -0.0002

Data Index: 317788 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2900. Min Act: -0.0002

Data Index: 514354 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2794. Min Act: -0.0002

Data Index: 278649 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2790. Min Act: -0.0002

Data Index: 1153175 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2994. Min Act: -0.0002

Data Index: 976684 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.3075. Min Act: -0.0002

Data Index: 1065065 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2683. Min Act: -0.0002

Data Index: 1020502 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2623. Min Act: -0.0002

Data Index: 913170 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2742. Min Act: -0.0002

Data Index: 1025306 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2943. Min Act: -0.0002

Data Index: 553104 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2768. Min Act: -0.0002

Data Index: 423486 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.3327. Min Range: -0.3327

Max Act: 0.2768. Min Act: -0.0002

Data Index: 1224005 (C4 (Web Text))

Max Activating Token Index: 358