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

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

Neuron 1664 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.5344. Min Act: 0.0000

Data Index: 215419 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.5631. Min Act: -0.0000

Data Index: 65545 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1081436 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.4175. Min Act: -0.0000

Data Index: 79696 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.4399. Min Act: 0.0000

Data Index: 1042095 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3935. Min Act: -0.0000

Data Index: 401344 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3890. Min Act: -0.0000

Data Index: 33097 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1175537 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3919. Min Act: 0.0000

Data Index: 664419 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3706. Min Act: -0.0000

Data Index: 275880 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1225473 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3755. Min Act: -0.0000

Data Index: 7458 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1143082 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3436. Min Act: -0.0000

Data Index: 777977 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3262. Min Act: -0.0000

Data Index: 893237 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3484. Min Act: -0.0000

Data Index: 135040 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3486. Min Act: 0.0000

Data Index: 23953 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3420. Min Act: -0.0000

Data Index: 667715 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3422. Min Act: -0.0000

Data Index: 948540 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3340. Min Act: -0.0000

Data Index: 62676 (C4 (Web Text))

Max Activating Token Index: 763