Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3983. Min Range: -1.3983

Max Act: 1.3983. Min Act: -0.0001

Data Index: 685588 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 1.3983. Min Range: -1.3983

Max Act: 1.0966. Min Act: -0.0000

Data Index: 146949 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 1.3983. Min Range: -1.3983

Max Act: 1.0600. Min Act: -0.0000

Data Index: 757208 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 1.3983. Min Range: -1.3983

Max Act: 1.1199. Min Act: -0.0001

Data Index: 784150 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.9735. Min Act: -0.0000

Data Index: 941008 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.7441. Min Act: -0.0000

Data Index: 533424 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.7316. Min Act: -0.0000

Data Index: 531071 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.5581. Min Act: -0.0000

Data Index: 662857 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.5430. Min Act: -0.0000

Data Index: 545600 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.5014. Min Act: -0.0001

Data Index: 882435 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.5593. Min Act: -0.0000

Data Index: 311302 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.5477. Min Act: -0.0001

Data Index: 189987 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.5099. Min Act: -0.0000

Data Index: 423828 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.5023. Min Act: -0.0000

Data Index: 77850 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.4762. Min Act: -0.0000

Data Index: 785481 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1080887 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.4735. Min Act: -0.0000

Data Index: 431858 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.4588. Min Act: -0.0000

Data Index: 772277 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.4793. Min Act: 0.0001

Data Index: 1627518 (Python Code)

Max Activating Token Index: 816

Text #19

Max Range: 1.3983. Min Range: -1.3983

Max Act: 0.4642. Min Act: -0.0000

Data Index: 415408 (C4 (Web Text))

Max Activating Token Index: 238