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

Dataset: The Pile

Neuron 3926 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0638. Min Range: -1.0638

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1046555 (The Pile)

Max Activating Token Index: 931

Text #1

Max Range: 1.0638. Min Range: -1.0638

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1380470 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.8942. Min Act: -0.0000

Data Index: 37960 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.8333. Min Act: -0.0000

Data Index: 590897 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.8282. Min Act: -0.0000

Data Index: 429064 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.8379. Min Act: -0.0000

Data Index: 492008 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.8732. Min Act: -0.0000

Data Index: 1263264 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7667. Min Act: -0.0000

Data Index: 211035 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7061. Min Act: -0.0000

Data Index: 814902 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7229. Min Act: -0.0000

Data Index: 417543 (The Pile)

Max Activating Token Index: 257

Text #10

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1151816 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.6352. Min Act: -0.0000

Data Index: 113028 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1217887 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7521. Min Act: -0.0000

Data Index: 508859 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.6662. Min Act: -0.0000

Data Index: 925327 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.6504. Min Act: -0.0000

Data Index: 319688 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1718417 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1968928 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.6306. Min Act: -0.0000

Data Index: 808331 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.6570. Min Act: -0.0000

Data Index: 853728 (The Pile)

Max Activating Token Index: 330