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

Dataset: The Pile

Neuron 4118 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: 1.4952. Min Range: -1.4952

Max Act: 1.4197. Min Act: -0.0000

Data Index: 858619 (The Pile)

Max Activating Token Index: 659

Text #1

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4666. Min Act: -0.0000

Data Index: 1450151 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4952. Min Act: -0.0000

Data Index: 242259 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4949. Min Act: -0.0000

Data Index: 1298033 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1292774 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1680661 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3044. Min Act: -0.0000

Data Index: 822544 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1319093 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1925611 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2976. Min Act: -0.0000

Data Index: 1816726 (The Pile)

Max Activating Token Index: 5

Text #10

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2085. Min Act: -0.0000

Data Index: 141432 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2041. Min Act: -0.0000

Data Index: 614805 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1809. Min Act: -0.0000

Data Index: 241659 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1177516 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1163263 (The Pile)

Max Activating Token Index: 624

Text #15

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1004. Min Act: -0.0000

Data Index: 934946 (The Pile)

Max Activating Token Index: 405

Text #16

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1524. Min Act: -0.0000

Data Index: 1870197 (The Pile)

Max Activating Token Index: 303

Text #17

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.1299. Min Act: -0.0000

Data Index: 851982 (The Pile)

Max Activating Token Index: 947

Text #18

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.0675. Min Act: -0.0000

Data Index: 376285 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.0595. Min Act: -0.0000

Data Index: 583333 (The Pile)

Max Activating Token Index: 411