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

Dataset: The Pile

Neuron 996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.4046. Min Act: -0.0000

Data Index: 103150 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2600. Min Act: -0.0000

Data Index: 802796 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1915755 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2635. Min Act: -0.0000

Data Index: 81187 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1244827 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2119. Min Act: -0.0000

Data Index: 710980 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1720250 (The Pile)

Max Activating Token Index: 999

Text #7

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1127774 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2101. Min Act: -0.0000

Data Index: 231039 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2083. Min Act: -0.0000

Data Index: 390859 (The Pile)

Max Activating Token Index: 765

Text #10

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1991089 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1350756 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.1983. Min Act: -0.0000

Data Index: 288503 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.1986. Min Act: -0.0000

Data Index: 8539 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2039. Min Act: -0.0000

Data Index: 514887 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2179. Min Act: -0.0000

Data Index: 264156 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.1932. Min Act: -0.0000

Data Index: 513136 (The Pile)

Max Activating Token Index: 815

Text #17

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1113750 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.1733. Min Act: -0.0000

Data Index: 500785 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1326285 (The Pile)

Max Activating Token Index: 556