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

Dataset: The Pile

Neuron 110 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1264. Min Range: -3.1264

Max Act: 3.1264. Min Act: -0.0000

Data Index: 1808866 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.9554. Min Act: -0.0000

Data Index: 1116284 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.8276. Min Act: -0.0000

Data Index: 1382229 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.8315. Min Act: -0.0000

Data Index: 1571904 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.5841. Min Act: -0.0000

Data Index: 14562 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.3921. Min Act: -0.0000

Data Index: 366072 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.4208. Min Act: -0.0000

Data Index: 475200 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.6159. Min Act: -0.0000

Data Index: 512341 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.2505. Min Act: -0.0000

Data Index: 506487 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1787420 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.3716. Min Act: -0.0000

Data Index: 1745888 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.2213. Min Act: -0.0000

Data Index: 750084 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.0828. Min Act: -0.0000

Data Index: 1927645 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.2853. Min Act: -0.0000

Data Index: 1614058 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.3009. Min Act: -0.0000

Data Index: 1095117 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.1336. Min Act: -0.0000

Data Index: 738528 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.2243. Min Act: -0.0000

Data Index: 57887 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.3449. Min Act: -0.0000

Data Index: 726464 (The Pile)

Max Activating Token Index: 319

Text #18

Max Range: 3.1264. Min Range: -3.1264

Max Act: 2.1087. Min Act: -0.0000

Data Index: 150233 (The Pile)

Max Activating Token Index: 318

Text #19

Max Range: 3.1264. Min Range: -3.1264

Max Act: 1.9491. Min Act: -0.0000

Data Index: 630696 (The Pile)

Max Activating Token Index: 113