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

Dataset: The Pile

Neuron 3484 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1350627 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3343. Min Act: -0.0000

Data Index: 527121 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1583023 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3194. Min Act: -0.0000

Data Index: 495033 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3069. Min Act: -0.0000

Data Index: 882253 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2696. Min Act: -0.0000

Data Index: 328675 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1000282 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2683. Min Act: -0.0000

Data Index: 513658 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2493. Min Act: -0.0000

Data Index: 506241 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2647. Min Act: -0.0000

Data Index: 344289 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2539. Min Act: -0.0000

Data Index: 869451 (The Pile)

Max Activating Token Index: 170

Text #11

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1865181 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2542. Min Act: -0.0000

Data Index: 828801 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2369. Min Act: -0.0000

Data Index: 845164 (The Pile)

Max Activating Token Index: 274

Text #14

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2607. Min Act: -0.0000

Data Index: 508854 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1816616 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1956051 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2609. Min Act: -0.0000

Data Index: 892252 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2456. Min Act: -0.0000

Data Index: 964942 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2602. Min Act: -0.0000

Data Index: 766152 (The Pile)

Max Activating Token Index: 711