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

Dataset: The Pile

Neuron 2370 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.6237. Min Act: -0.0000

Data Index: 169315 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7289. Min Act: -0.0000

Data Index: 794890 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7179. Min Act: -0.0000

Data Index: 1680333 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7258. Min Act: -0.0000

Data Index: 1845240 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8350. Min Act: -0.0000

Data Index: 798616 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7686. Min Act: -0.0000

Data Index: 1810142 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.4992. Min Act: -0.0000

Data Index: 699868 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.6792. Min Act: -0.0000

Data Index: 468390 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.4508. Min Act: -0.0000

Data Index: 1881018 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.2467. Min Act: -0.0000

Data Index: 498789 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.5709. Min Act: -0.0000

Data Index: 537307 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.2482. Min Act: -0.0000

Data Index: 562055 (The Pile)

Max Activating Token Index: 643

Text #12

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.2227. Min Act: -0.0000

Data Index: 555268 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.5284. Min Act: -0.0000

Data Index: 948184 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.2332. Min Act: -0.0000

Data Index: 1383705 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.2935. Min Act: -0.0000

Data Index: 482049 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.2626. Min Act: -0.0000

Data Index: 71869 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.2380. Min Act: -0.0000

Data Index: 720252 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.2448. Min Act: -0.0000

Data Index: 1744848 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.1072. Min Act: -0.0000

Data Index: 1403349 (The Pile)

Max Activating Token Index: 134