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

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

Neuron 2446 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.8705. Min Act: -0.0002

Data Index: 20526 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.8470. Min Act: -0.0003

Data Index: 511357 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7734. Min Act: -0.0002

Data Index: 354336 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7567. Min Act: -0.0002

Data Index: 146642 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7608. Min Act: -0.0002

Data Index: 267527 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7372. Min Act: -0.0002

Data Index: 324353 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7178. Min Act: -0.0002

Data Index: 1242254 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7072. Min Act: -0.0002

Data Index: 809482 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7026. Min Act: -0.0002

Data Index: 1243482 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6960. Min Act: -0.0002

Data Index: 881367 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6907. Min Act: -0.0002

Data Index: 1073331 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7062. Min Act: -0.0002

Data Index: 690342 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7007. Min Act: -0.0002

Data Index: 1042543 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6907. Min Act: -0.0002

Data Index: 63447 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6914. Min Act: -0.0002

Data Index: 31224 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6792. Min Act: -0.0003

Data Index: 1348920 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6769. Min Act: -0.0002

Data Index: 417764 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6787. Min Act: -0.0002

Data Index: 402653 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6770. Min Act: -0.0002

Data Index: 69509 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6680. Min Act: -0.0002

Data Index: 947460 (C4 (Web Text))

Max Activating Token Index: 222