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

Dataset: The Pile

Neuron 3955 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.7175. Min Act: -0.0000

Data Index: 144863 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.4396. Min Act: -0.0000

Data Index: 94533 (The Pile)

Max Activating Token Index: 851

Text #2

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.4368. Min Act: -0.0000

Data Index: 773685 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.4010. Min Act: -0.0000

Data Index: 317728 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.2240. Min Act: -0.0000

Data Index: 701169 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.0916. Min Act: -0.0000

Data Index: 1097269 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.0815. Min Act: -0.0000

Data Index: 1831366 (The Pile)

Max Activating Token Index: 679

Text #7

Max Range: 3.7175. Min Range: -3.7175

Max Act: 2.9372. Min Act: -0.0000

Data Index: 917463 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.1454. Min Act: -0.0000

Data Index: 898511 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.0039. Min Act: -0.0000

Data Index: 840365 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 3.7175. Min Range: -3.7175

Max Act: 2.9357. Min Act: -0.0000

Data Index: 128611 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 3.7175. Min Range: -3.7175

Max Act: 2.8203. Min Act: -0.0000

Data Index: 1622461 (The Pile)

Max Activating Token Index: 809

Text #12

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.1005. Min Act: -0.0000

Data Index: 575218 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 3.7175. Min Range: -3.7175

Max Act: 2.9254. Min Act: -0.0000

Data Index: 899345 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.0395. Min Act: -0.0000

Data Index: 1823763 (The Pile)

Max Activating Token Index: 448

Text #15

Max Range: 3.7175. Min Range: -3.7175

Max Act: 2.8857. Min Act: -0.0000

Data Index: 881899 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 3.7175. Min Range: -3.7175

Max Act: 2.8743. Min Act: -0.0000

Data Index: 803006 (The Pile)

Max Activating Token Index: 326

Text #17

Max Range: 3.7175. Min Range: -3.7175

Max Act: 2.7319. Min Act: -0.0000

Data Index: 1258785 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 3.7175. Min Range: -3.7175

Max Act: 2.8382. Min Act: -0.0000

Data Index: 339297 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 3.7175. Min Range: -3.7175

Max Act: 2.8235. Min Act: -0.0000

Data Index: 1470566 (The Pile)

Max Activating Token Index: 313