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

Dataset: The Pile

Neuron 2534 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: 1.3996. Min Range: -1.3996

Max Act: 1.2382. Min Act: -0.0000

Data Index: 5141 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.3996. Min Act: -0.0000

Data Index: 266703 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1324316 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2542. Min Act: -0.0000

Data Index: 180513 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.3831. Min Act: -0.0000

Data Index: 756971 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2343. Min Act: -0.0000

Data Index: 9744 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1559811 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2828. Min Act: -0.0000

Data Index: 216520 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2779. Min Act: -0.0000

Data Index: 1542902 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1844179 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1677503 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2304. Min Act: -0.0000

Data Index: 989905 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.0455. Min Act: -0.0000

Data Index: 414370 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.1964. Min Act: -0.0000

Data Index: 596423 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2229. Min Act: -0.0000

Data Index: 566036 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.1872. Min Act: -0.0000

Data Index: 1432285 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1540582 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1163210 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1113754 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 1.3996. Min Range: -1.3996

Max Act: 1.1371. Min Act: -0.0000

Data Index: 1844174 (The Pile)

Max Activating Token Index: 567