Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3840 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1328825 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1547636 (The Pile)

Max Activating Token Index: 507

Text #2

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1300054 (The Pile)

Max Activating Token Index: 278

Text #3

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6318. Min Act: -0.0000

Data Index: 558681 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6217. Min Act: -0.0000

Data Index: 461396 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1936777 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1837454 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1369720 (The Pile)

Max Activating Token Index: 913

Text #8

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1861436 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1732711 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1842917 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5443. Min Act: -0.0000

Data Index: 126462 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5772. Min Act: -0.0000

Data Index: 65167 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5312. Min Act: -0.0000

Data Index: 905550 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1491030 (The Pile)

Max Activating Token Index: 871

Text #15

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5646. Min Act: -0.0000

Data Index: 412415 (The Pile)

Max Activating Token Index: 210

Text #16

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5264. Min Act: -0.0000

Data Index: 299572 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1318742 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5735. Min Act: -0.0000

Data Index: 408816 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.5065. Min Act: -0.0000

Data Index: 315959 (The Pile)

Max Activating Token Index: 923