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

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

Neuron 3867 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0386. Min Range: -1.0386

Max Act: 1.0386. Min Act: -0.0000

Data Index: 939368 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.9594. Min Act: -0.0000

Data Index: 393951 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7697. Min Act: -0.0000

Data Index: 756074 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7929. Min Act: -0.0000

Data Index: 267179 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7519. Min Act: -0.0000

Data Index: 434549 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7265. Min Act: -0.0000

Data Index: 136834 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7568. Min Act: -0.0000

Data Index: 4808 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7317. Min Act: -0.0000

Data Index: 63958 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7686. Min Act: -0.0000

Data Index: 909606 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1090491 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7061. Min Act: -0.0000

Data Index: 515917 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7037. Min Act: -0.0000

Data Index: 215095 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1314067 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6785. Min Act: -0.0000

Data Index: 387606 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6989. Min Act: -0.0000

Data Index: 468261 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6677. Min Act: -0.0000

Data Index: 532018 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6570. Min Act: -0.0000

Data Index: 918918 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6456. Min Act: -0.0000

Data Index: 998247 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6100. Min Act: -0.0000

Data Index: 858165 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6000. Min Act: -0.0000

Data Index: 685369 (C4 (Web Text))

Max Activating Token Index: 512