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

Dataset: The Pile

Neuron 1440 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.5208. Min Act: -0.0000

Data Index: 125747 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4793. Min Act: -0.0000

Data Index: 892304 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1155331 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.4012. Min Act: -0.0000

Data Index: 199544 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1305887 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1695098 (The Pile)

Max Activating Token Index: 39

Text #6

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3076. Min Act: -0.0000

Data Index: 187147 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3465. Min Act: -0.0000

Data Index: 40969 (The Pile)

Max Activating Token Index: 452

Text #8

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3378. Min Act: -0.0000

Data Index: 284129 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1325674 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3512. Min Act: -0.0000

Data Index: 637244 (The Pile)

Max Activating Token Index: 588

Text #11

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1743809 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3002. Min Act: -0.0000

Data Index: 611606 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1637695 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3417. Min Act: -0.0000

Data Index: 983611 (The Pile)

Max Activating Token Index: 408

Text #15

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1747250 (The Pile)

Max Activating Token Index: 590

Text #16

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.2760. Min Act: -0.0000

Data Index: 252067 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3100. Min Act: -0.0000

Data Index: 878254 (The Pile)

Max Activating Token Index: 765

Text #18

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1970646 (The Pile)

Max Activating Token Index: 335

Text #19

Max Range: 0.5208. Min Range: -0.5208

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1000985 (The Pile)

Max Activating Token Index: 727