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

Dataset: The Pile

Neuron 3416 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: 1.4616. Min Range: -1.4616

Max Act: 1.4616. Min Act: -0.0000

Data Index: 990118 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.4189. Min Act: -0.0000

Data Index: 850272 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.4437. Min Act: -0.0000

Data Index: 651499 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.4171. Min Act: -0.0000

Data Index: 253748 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1924925 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.3603. Min Act: -0.0000

Data Index: 1101715 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.3882. Min Act: -0.0000

Data Index: 541523 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1570638 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.3271. Min Act: -0.0000

Data Index: 267968 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.3056. Min Act: -0.0000

Data Index: 627763 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2710. Min Act: -0.0000

Data Index: 1853046 (The Pile)

Max Activating Token Index: 367

Text #11

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.3274. Min Act: -0.0000

Data Index: 381313 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2827. Min Act: -0.0000

Data Index: 259793 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2699. Min Act: -0.0000

Data Index: 474953 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2717. Min Act: -0.0000

Data Index: 1359435 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1517717 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.1895. Min Act: -0.0000

Data Index: 881774 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2624. Min Act: -0.0000

Data Index: 629853 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1781254 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2494. Min Act: -0.0000

Data Index: 514196 (The Pile)

Max Activating Token Index: 17