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

Dataset: The Pile

Neuron 790 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: 0.5031. Min Range: -0.5031

Max Act: 0.5031. Min Act: -0.0000

Data Index: 881274 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1673982 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1471952 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4126. Min Act: -0.0000

Data Index: 478963 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1123349 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3987. Min Act: -0.0000

Data Index: 986791 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1898780 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1389307 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4206. Min Act: -0.0000

Data Index: 931807 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1156168 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4197. Min Act: -0.0000

Data Index: 922679 (The Pile)

Max Activating Token Index: 614

Text #11

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1225449 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3992. Min Act: -0.0000

Data Index: 153093 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4080. Min Act: -0.0000

Data Index: 994937 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1997077 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1720156 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4214. Min Act: -0.0000

Data Index: 957142 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3664. Min Act: -0.0000

Data Index: 130092 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4034. Min Act: -0.0000

Data Index: 556020 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3634. Min Act: -0.0000

Data Index: 954493 (The Pile)

Max Activating Token Index: 278