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

Dataset: The Pile

Neuron 2985 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: 0.8091. Min Range: -0.8091

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1253118 (The Pile)

Max Activating Token Index: 943

Text #1

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.7185. Min Act: -0.0000

Data Index: 828292 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.8091. Min Act: -0.0000

Data Index: 952638 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1698535 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.7265. Min Act: -0.0000

Data Index: 964225 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1532133 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6551. Min Act: -0.0000

Data Index: 832918 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1096629 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1924822 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1752908 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6986. Min Act: -0.0000

Data Index: 431814 (The Pile)

Max Activating Token Index: 956

Text #11

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6671. Min Act: -0.0000

Data Index: 33560 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1930554 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1625261 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1516459 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6968. Min Act: -0.0000

Data Index: 916398 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6457. Min Act: -0.0000

Data Index: 942372 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1364474 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6822. Min Act: -0.0000

Data Index: 689645 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6826. Min Act: -0.0000

Data Index: 131388 (The Pile)

Max Activating Token Index: 763