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

Dataset: The Pile

Neuron 1429 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0086. Min Act: -0.0000

Data Index: 1973358 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0000

Data Index: 317089 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0069. Min Act: -0.0000

Data Index: 119766 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0068. Min Act: -0.0000

Data Index: 1442003 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0067. Min Act: -0.0000

Data Index: 1840374 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0068. Min Act: -0.0000

Data Index: 1805216 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0066. Min Act: -0.0000

Data Index: 1979949 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0065. Min Act: -0.0000

Data Index: 336103 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0064. Min Act: -0.0000

Data Index: 1803858 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0064. Min Act: -0.0000

Data Index: 870600 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0063. Min Act: -0.0000

Data Index: 1188064 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0063. Min Act: -0.0000

Data Index: 1414983 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0062. Min Act: -0.0000

Data Index: 1420011 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0061. Min Act: -0.0000

Data Index: 292776 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0061. Min Act: -0.0000

Data Index: 1026051 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0061. Min Act: -0.0000

Data Index: 1586001 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0061. Min Act: -0.0000

Data Index: 531491 (The Pile)

Max Activating Token Index: 398

Text #17

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0061. Min Act: -0.0000

Data Index: 440310 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0060. Min Act: -0.0000

Data Index: 1753843 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0060. Min Act: -0.0000

Data Index: 1687954 (The Pile)

Max Activating Token Index: 405