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

Dataset: The Pile

Neuron 1099 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: 0.4024. Min Range: -0.4024

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1844104 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3608. Min Act: -0.0000

Data Index: 298348 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3914. Min Act: -0.0000

Data Index: 289551 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3371. Min Act: -0.0000

Data Index: 410808 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1618517 (The Pile)

Max Activating Token Index: 579

Text #5

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1061370 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3055. Min Act: -0.0000

Data Index: 577869 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1143008 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1566364 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3106. Min Act: -0.0000

Data Index: 930705 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1737530 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1638518 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1863406 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1752449 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1502545 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1444026 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3060. Min Act: -0.0000

Data Index: 165071 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2850. Min Act: -0.0000

Data Index: 517194 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2673. Min Act: -0.0000

Data Index: 633753 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1521596 (The Pile)

Max Activating Token Index: 467