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

Dataset: The Pile

Neuron 3915 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: 0.8620. Min Range: -0.8620

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1201851 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6739. Min Act: -0.0000

Data Index: 841488 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1143121 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1822658 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1311615 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1693038 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5460. Min Act: -0.0000

Data Index: 193464 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5626. Min Act: -0.0000

Data Index: 808987 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5106. Min Act: -0.0000

Data Index: 323626 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1768097 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.4758. Min Act: -0.0000

Data Index: 438749 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.4984. Min Act: -0.0000

Data Index: 245287 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.4971. Min Act: -0.0000

Data Index: 566831 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.4613. Min Act: -0.0000

Data Index: 476435 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5021. Min Act: -0.0000

Data Index: 585963 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5156. Min Act: -0.0000

Data Index: 836402 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.4759. Min Act: -0.0000

Data Index: 317803 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.4476. Min Act: -0.0000

Data Index: 729961 (The Pile)

Max Activating Token Index: 773

Text #18

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1034448 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.4273. Min Act: -0.0000

Data Index: 279177 (The Pile)

Max Activating Token Index: 932