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

Dataset: The Pile

Neuron 503 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1657817 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1018922 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1608435 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1032225 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1125. Min Act: 0.0000

Data Index: 1792071 (The Pile)

Max Activating Token Index: 483

Text #5

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1043. Min Act: 0.0000

Data Index: 368518 (The Pile)

Max Activating Token Index: 636

Text #6

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1683807 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1059. Min Act: 0.0000

Data Index: 799997 (The Pile)

Max Activating Token Index: 280

Text #8

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1260768 (The Pile)

Max Activating Token Index: 462

Text #9

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0988. Min Act: -0.0000

Data Index: 635005 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0992. Min Act: -0.0000

Data Index: 131047 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0980. Min Act: -0.0000

Data Index: 769982 (The Pile)

Max Activating Token Index: 855

Text #12

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1105807 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1049. Min Act: -0.0000

Data Index: 520497 (The Pile)

Max Activating Token Index: 29

Text #14

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0930. Min Act: -0.0000

Data Index: 883379 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1062. Min Act: -0.0000

Data Index: 248774 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1729830 (The Pile)

Max Activating Token Index: 437

Text #17

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0950. Min Act: 0.0000

Data Index: 1009482 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0900. Min Act: -0.0000

Data Index: 365778 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1795801 (The Pile)

Max Activating Token Index: 757