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

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

Neuron 1423 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: 0.6692. Min Range: -0.6692

Max Act: 0.6692. Min Act: -0.0000

Data Index: 689117 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5547. Min Act: -0.0000

Data Index: 861657 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5055. Min Act: -0.0000

Data Index: 506475 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1183222 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4884. Min Act: -0.0000

Data Index: 97948 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1237833 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4654. Min Act: -0.0000

Data Index: 616261 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4427. Min Act: -0.0000

Data Index: 116249 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4695. Min Act: -0.0000

Data Index: 464810 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4366. Min Act: -0.0000

Data Index: 39432 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4085. Min Act: -0.0000

Data Index: 486312 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1165230 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.3972. Min Act: -0.0000

Data Index: 815252 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4102. Min Act: -0.0000

Data Index: 411749 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1186900 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.3969. Min Act: -0.0000

Data Index: 759691 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.3754. Min Act: -0.0000

Data Index: 290118 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.3797. Min Act: -0.0000

Data Index: 494604 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.3794. Min Act: -0.0000

Data Index: 376681 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.3776. Min Act: -0.0000

Data Index: 828276 (C4 (Web Text))

Max Activating Token Index: 385