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

Dataset: The Pile

Neuron 705 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: 5.3987. Min Range: -5.3987

Max Act: 5.3987. Min Act: -0.0000

Data Index: 577019 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 5.3987. Min Range: -5.3987

Max Act: 5.2174. Min Act: -0.0000

Data Index: 986302 (The Pile)

Max Activating Token Index: 791

Text #2

Max Range: 5.3987. Min Range: -5.3987

Max Act: 4.4771. Min Act: -0.0000

Data Index: 393906 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 5.3987. Min Range: -5.3987

Max Act: 4.2128. Min Act: -0.0000

Data Index: 1652520 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 5.3987. Min Range: -5.3987

Max Act: 4.8126. Min Act: -0.0000

Data Index: 1963500 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 5.3987. Min Range: -5.3987

Max Act: 4.1050. Min Act: -0.0000

Data Index: 1341197 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 5.3987. Min Range: -5.3987

Max Act: 4.4665. Min Act: -0.0000

Data Index: 1693252 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 5.3987. Min Range: -5.3987

Max Act: 4.1280. Min Act: -0.0000

Data Index: 1784891 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 5.3987. Min Range: -5.3987

Max Act: 4.0894. Min Act: -0.0000

Data Index: 499074 (The Pile)

Max Activating Token Index: 939

Text #9

Max Range: 5.3987. Min Range: -5.3987

Max Act: 4.0709. Min Act: -0.0000

Data Index: 341314 (The Pile)

Max Activating Token Index: 662

Text #10

Max Range: 5.3987. Min Range: -5.3987

Max Act: 4.0504. Min Act: -0.0000

Data Index: 421859 (The Pile)

Max Activating Token Index: 854

Text #11

Max Range: 5.3987. Min Range: -5.3987

Max Act: 3.9305. Min Act: -0.0000

Data Index: 284026 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 5.3987. Min Range: -5.3987

Max Act: 3.9341. Min Act: -0.0000

Data Index: 1938899 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 5.3987. Min Range: -5.3987

Max Act: 3.9557. Min Act: -0.0000

Data Index: 1318508 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 5.3987. Min Range: -5.3987

Max Act: 3.6293. Min Act: -0.0000

Data Index: 251912 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 5.3987. Min Range: -5.3987

Max Act: 3.9259. Min Act: -0.0000

Data Index: 492816 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 5.3987. Min Range: -5.3987

Max Act: 3.9177. Min Act: -0.0000

Data Index: 614567 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 5.3987. Min Range: -5.3987

Max Act: 3.7531. Min Act: -0.0000

Data Index: 822122 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 5.3987. Min Range: -5.3987

Max Act: 3.8933. Min Act: -0.0000

Data Index: 235744 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 5.3987. Min Range: -5.3987

Max Act: 3.7955. Min Act: -0.0000

Data Index: 45834 (The Pile)

Max Activating Token Index: 35