Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2577 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.6465. Min Act: -0.0001

Data Index: 850347 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.6730. Min Act: -0.0000

Data Index: 1107302 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4961. Min Act: -0.0000

Data Index: 32481 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.5009. Min Act: -0.0000

Data Index: 487087 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.5028. Min Act: -0.0001

Data Index: 774925 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4068. Min Act: -0.0000

Data Index: 346801 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.6289. Min Act: -0.0001

Data Index: 1005533 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4401. Min Act: -0.0000

Data Index: 775025 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4227. Min Act: -0.0000

Data Index: 402500 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.3710. Min Act: -0.0000

Data Index: 408128 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.3779. Min Act: -0.0000

Data Index: 459260 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.2624. Min Act: -0.0001

Data Index: 1204550 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4333. Min Act: -0.0001

Data Index: 1188466 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.3149. Min Act: -0.0001

Data Index: 541775 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1287863 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.1375. Min Act: -0.0000

Data Index: 43620 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4106. Min Act: -0.0000

Data Index: 670145 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.3042. Min Act: -0.0000

Data Index: 1058452 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.4487. Min Act: -0.0000

Data Index: 989068 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 1.6730. Min Range: -1.6730

Max Act: 1.3293. Min Act: -0.0001

Data Index: 1153442 (C4 (Web Text))

Max Activating Token Index: 586