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

Dataset: The Pile

Neuron 1177 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: 1.6305. Min Range: -1.6305

Max Act: 1.6305. Min Act: -0.0000

Data Index: 1557257 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5577. Min Act: -0.0000

Data Index: 596525 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.4915. Min Act: -0.0000

Data Index: 680429 (The Pile)

Max Activating Token Index: 106

Text #3

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.3568. Min Act: -0.0000

Data Index: 1475759 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1356039 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1382273 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.2944. Min Act: -0.0000

Data Index: 525863 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.4985. Min Act: -0.0000

Data Index: 896335 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.3253. Min Act: -0.0000

Data Index: 1954520 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1493345 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.2331. Min Act: -0.0000

Data Index: 1342313 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.2381. Min Act: 0.0000

Data Index: 329131 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.3035. Min Act: -0.0000

Data Index: 1318306 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.3392. Min Act: -0.0000

Data Index: 990494 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.1815. Min Act: -0.0000

Data Index: 298572 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1641038 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.2422. Min Act: 0.0000

Data Index: 1859768 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.2584. Min Act: -0.0000

Data Index: 639299 (The Pile)

Max Activating Token Index: 81

Text #18

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.1849. Min Act: -0.0000

Data Index: 711895 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.1819. Min Act: 0.0000

Data Index: 208264 (The Pile)

Max Activating Token Index: 1010