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

Dataset: The Pile

Neuron 2981 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: 0.5345. Min Range: -0.5345

Max Act: 0.5345. Min Act: -0.0000

Data Index: 706661 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4419. Min Act: -0.0000

Data Index: 554945 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4569. Min Act: -0.0000

Data Index: 597501 (The Pile)

Max Activating Token Index: 935

Text #3

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1011877 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1210489 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1048880 (The Pile)

Max Activating Token Index: 943

Text #6

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1831752 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1832207 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3835. Min Act: -0.0000

Data Index: 839773 (The Pile)

Max Activating Token Index: 373

Text #9

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3936. Min Act: -0.0000

Data Index: 605862 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1121534 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1655252 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3513. Min Act: -0.0000

Data Index: 770785 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1923593 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3620. Min Act: -0.0000

Data Index: 971867 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3367. Min Act: -0.0000

Data Index: 227791 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1913849 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1244581 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3363. Min Act: -0.0000

Data Index: 571783 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1964131 (The Pile)

Max Activating Token Index: 717