Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 731 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.6767. Min Act: -0.0000

Data Index: 309636 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.6417. Min Act: -0.0001

Data Index: 1398268 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.6320. Min Act: -0.0000

Data Index: 533307 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.6288. Min Act: -0.0001

Data Index: 1312399 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1172672 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5744. Min Act: -0.0000

Data Index: 824057 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1760839 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5379. Min Act: -0.0000

Data Index: 682411 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1059432 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5649. Min Act: -0.0000

Data Index: 950447 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1986369 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4969. Min Act: -0.0000

Data Index: 522920 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5271. Min Act: -0.0001

Data Index: 772891 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4873. Min Act: -0.0000

Data Index: 418858 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5049. Min Act: -0.0000

Data Index: 245959 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5047. Min Act: -0.0000

Data Index: 724423 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1811298 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1554808 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4687. Min Act: -0.0000

Data Index: 829024 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1045435 (The Pile)

Max Activating Token Index: 315