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

Dataset: The Pile

Neuron 2279 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.7227. Min Act: -0.0000

Data Index: 433649 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1498659 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1340481 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5317. Min Act: -0.0000

Data Index: 514947 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1789445 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1288066 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5322. Min Act: -0.0000

Data Index: 389652 (The Pile)

Max Activating Token Index: 9

Text #7

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1238907 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1930026 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4894. Min Act: -0.0000

Data Index: 358485 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1826033 (The Pile)

Max Activating Token Index: 411

Text #11

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4992. Min Act: -0.0000

Data Index: 505077 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1295215 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5123. Min Act: -0.0000

Data Index: 548440 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1720430 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5006. Min Act: -0.0000

Data Index: 721341 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1768942 (The Pile)

Max Activating Token Index: 711

Text #17

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1787378 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4494. Min Act: -0.0000

Data Index: 377433 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1522437 (The Pile)

Max Activating Token Index: 714