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

Dataset: The Pile

Neuron 3903 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: 0.4964. Min Range: -0.4964

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1675057 (The Pile)

Max Activating Token Index: 309

Text #1

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1104879 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4752. Min Act: -0.0000

Data Index: 181933 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4679. Min Act: -0.0000

Data Index: 135704 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1094711 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1339760 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3750. Min Act: -0.0000

Data Index: 586499 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1443186 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3939. Min Act: -0.0000

Data Index: 346580 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1740103 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1063100 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3403. Min Act: -0.0000

Data Index: 951941 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3305. Min Act: -0.0000

Data Index: 639973 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1911125 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1136878 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3385. Min Act: -0.0000

Data Index: 773319 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3665. Min Act: -0.0000

Data Index: 219929 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3587. Min Act: -0.0000

Data Index: 291058 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3546. Min Act: -0.0000

Data Index: 529769 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1242122 (The Pile)

Max Activating Token Index: 920