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

Dataset: The Pile

Neuron 3040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1540422 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1214593 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.7146. Min Act: 0.0000

Data Index: 57027 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6073. Min Act: -0.0000

Data Index: 328714 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1678617 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6988. Min Act: 0.0000

Data Index: 612645 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1962291 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6528. Min Act: -0.0000

Data Index: 319971 (The Pile)

Max Activating Token Index: 487

Text #8

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1771816 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6450. Min Act: -0.0000

Data Index: 770692 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1055694 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1495616 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6400. Min Act: -0.0000

Data Index: 980554 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6636. Min Act: -0.0000

Data Index: 481303 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6087. Min Act: -0.0000

Data Index: 794652 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6748. Min Act: -0.0000

Data Index: 154853 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6674. Min Act: -0.0000

Data Index: 742121 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6240. Min Act: 0.0000

Data Index: 942510 (The Pile)

Max Activating Token Index: 939

Text #18

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1747998 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.5762. Min Act: 0.0000

Data Index: 1558358 (The Pile)

Max Activating Token Index: 763