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

Dataset: The Pile

Neuron 1745 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1372029 (The Pile)

Max Activating Token Index: 468

Text #1

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1448297 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1062307 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7630. Min Act: -0.0000

Data Index: 629288 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7167. Min Act: -0.0000

Data Index: 604302 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1218170 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1428210 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7592. Min Act: -0.0000

Data Index: 135133 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1158822 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1976464 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1623597 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1849780 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7414. Min Act: -0.0000

Data Index: 326837 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1313244 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6981. Min Act: -0.0000

Data Index: 245376 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6731. Min Act: -0.0000

Data Index: 928276 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1087803 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1670690 (The Pile)

Max Activating Token Index: 804

Text #18

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7780. Min Act: -0.0000

Data Index: 826290 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.6961. Min Act: -0.0000

Data Index: 729733 (The Pile)

Max Activating Token Index: 511