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

Dataset: The Pile

Neuron 3565 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: 1.0837. Min Range: -1.0837

Max Act: 1.0837. Min Act: -0.0000

Data Index: 591936 (The Pile)

Max Activating Token Index: 680

Text #1

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1650210 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1929815 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9227. Min Act: -0.0000

Data Index: 749639 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9339. Min Act: -0.0000

Data Index: 438136 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8736. Min Act: -0.0000

Data Index: 739980 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9470. Min Act: -0.0000

Data Index: 297034 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8583. Min Act: -0.0000

Data Index: 875181 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1092090 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1348638 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1149543 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.7823. Min Act: -0.0000

Data Index: 704136 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8276. Min Act: -0.0000

Data Index: 621568 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1843746 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1597815 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1195640 (The Pile)

Max Activating Token Index: 649

Text #16

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8165. Min Act: -0.0000

Data Index: 318355 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8214. Min Act: -0.0000

Data Index: 461415 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1408462 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1526102 (The Pile)

Max Activating Token Index: 46