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

Dataset: The Pile

Neuron 598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0987. Min Act: -0.0000

Data Index: 285462 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0520. Min Act: -0.0000

Data Index: 200333 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0636. Min Act: -0.0000

Data Index: 357946 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0872. Min Act: -0.0000

Data Index: 917671 (The Pile)

Max Activating Token Index: 230

Text #4

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1047. Min Act: -0.0000

Data Index: 1234897 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1230. Min Act: -0.0000

Data Index: 552433 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1686374 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1500753 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1233. Min Act: -0.0000

Data Index: 1057605 (The Pile)

Max Activating Token Index: 464

Text #9

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1016. Min Act: -0.0000

Data Index: 434282 (The Pile)

Max Activating Token Index: 466

Text #10

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9579. Min Act: -0.0000

Data Index: 529971 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0382. Min Act: -0.0000

Data Index: 917256 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0403. Min Act: -0.0000

Data Index: 590141 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1556980 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1974172 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.8159. Min Act: -0.0000

Data Index: 594234 (The Pile)

Max Activating Token Index: 820

Text #16

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1087877 (The Pile)

Max Activating Token Index: 414

Text #17

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9748. Min Act: -0.0000

Data Index: 397694 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9530. Min Act: -0.0000

Data Index: 772353 (The Pile)

Max Activating Token Index: 678

Text #19

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1487515 (The Pile)

Max Activating Token Index: 287