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

Dataset: The Pile

Neuron 2962 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: 0.2297. Min Range: -0.2297

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1096226 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2146. Min Act: -0.0000

Data Index: 307683 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1822419 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2044. Min Act: -0.0000

Data Index: 149440 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2106. Min Act: -0.0000

Data Index: 615039 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1503084 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2008. Min Act: -0.0000

Data Index: 834450 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2042. Min Act: -0.0000

Data Index: 244536 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2045. Min Act: 0.0000

Data Index: 705105 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1962. Min Act: -0.0000

Data Index: 540892 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1606353 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2080. Min Act: -0.0000

Data Index: 42365 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2003. Min Act: 0.0001

Data Index: 1897440 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1425430 (The Pile)

Max Activating Token Index: 539

Text #14

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2007. Min Act: -0.0000

Data Index: 447073 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1932. Min Act: -0.0000

Data Index: 583971 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1009424 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1024723 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1961810 (The Pile)

Max Activating Token Index: 740

Text #19

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2023. Min Act: -0.0000

Data Index: 212560 (The Pile)

Max Activating Token Index: 302