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

Dataset: The Pile

Neuron 3025 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: 1.2275. Min Range: -1.2275

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1593475 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0621. Min Act: -0.0000

Data Index: 527456 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0784. Min Act: -0.0000

Data Index: 444402 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1277588 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1759186 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1597228 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1850796 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9648. Min Act: -0.0000

Data Index: 173942 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8337. Min Act: -0.0000

Data Index: 990659 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1769294 (The Pile)

Max Activating Token Index: 745

Text #10

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1282086 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1818588 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1648389 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9258. Min Act: -0.0000

Data Index: 994663 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9741. Min Act: -0.0000

Data Index: 166799 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8502. Min Act: -0.0000

Data Index: 55831 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1904526 (The Pile)

Max Activating Token Index: 460

Text #17

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1235222 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1413363 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9103. Min Act: -0.0000

Data Index: 281987 (The Pile)

Max Activating Token Index: 576