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

Dataset: The Pile

Neuron 4015 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.8656. Min Act: -0.0000

Data Index: 594610 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6629. Min Act: -0.0000

Data Index: 453358 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1576832 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6697. Min Act: -0.0000

Data Index: 581529 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6922. Min Act: -0.0000

Data Index: 467268 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6692. Min Act: -0.0000

Data Index: 659177 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1016215 (The Pile)

Max Activating Token Index: 220

Text #7

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1624685 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5578. Min Act: -0.0000

Data Index: 226470 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5943. Min Act: -0.0000

Data Index: 236205 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5810. Min Act: 0.0000

Data Index: 309586 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.4901. Min Act: -0.0000

Data Index: 928575 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1934993 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1290078 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5045. Min Act: -0.0000

Data Index: 688363 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1648020 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.4861. Min Act: 0.0000

Data Index: 527770 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1530991 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5045. Min Act: -0.0000

Data Index: 530329 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1714398 (The Pile)

Max Activating Token Index: 504