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

Dataset: The Pile

Neuron 1596 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: 1.3384. Min Range: -1.3384

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1989354 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.0385. Min Act: -0.0000

Data Index: 124527 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9116. Min Act: -0.0000

Data Index: 908788 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9087. Min Act: -0.0000

Data Index: 57567 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9494. Min Act: -0.0000

Data Index: 732801 (The Pile)

Max Activating Token Index: 131

Text #5

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.8818. Min Act: -0.0000

Data Index: 690034 (The Pile)

Max Activating Token Index: 960

Text #6

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1031776 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.8085. Min Act: -0.0000

Data Index: 905298 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1319281 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.8451. Min Act: -0.0000

Data Index: 125441 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9084. Min Act: -0.0000

Data Index: 704101 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1773367 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.7326. Min Act: -0.0000

Data Index: 118157 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1794029 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1107217 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.7250. Min Act: -0.0000

Data Index: 435459 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.7888. Min Act: -0.0000

Data Index: 376706 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1298654 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.7340. Min Act: -0.0000

Data Index: 975267 (The Pile)

Max Activating Token Index: 525

Text #19

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.7341. Min Act: -0.0000

Data Index: 70946 (The Pile)

Max Activating Token Index: 598