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

Dataset: The Pile

Neuron 845 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: 5.5945. Min Range: -5.5945

Max Act: 5.5945. Min Act: -0.0000

Data Index: 1073450 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 5.5945. Min Range: -5.5945

Max Act: 4.4005. Min Act: -0.0000

Data Index: 1839364 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 5.5945. Min Range: -5.5945

Max Act: 4.4239. Min Act: -0.0000

Data Index: 772802 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.6518. Min Act: -0.0000

Data Index: 1197184 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.8326. Min Act: -0.0000

Data Index: 1334289 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.1750. Min Act: -0.0000

Data Index: 1914650 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.5289. Min Act: -0.0000

Data Index: 1149408 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.6087. Min Act: -0.0000

Data Index: 1315574 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.2757. Min Act: -0.0000

Data Index: 1284776 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.6532. Min Act: -0.0000

Data Index: 1410824 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.1048. Min Act: -0.0000

Data Index: 985757 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.4792. Min Act: -0.0000

Data Index: 1641675 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.7909. Min Act: -0.0000

Data Index: 1546919 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.0447. Min Act: -0.0000

Data Index: 818744 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.1794. Min Act: -0.0000

Data Index: 534680 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.2963. Min Act: -0.0000

Data Index: 1069374 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.1146. Min Act: -0.0000

Data Index: 1803226 (The Pile)

Max Activating Token Index: 699

Text #17

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.1068. Min Act: -0.0000

Data Index: 434735 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.4906. Min Act: -0.0000

Data Index: 737758 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 5.5945. Min Range: -5.5945

Max Act: 3.3372. Min Act: -0.0000

Data Index: 1667633 (The Pile)

Max Activating Token Index: 222