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

Dataset: The Pile

Neuron 4279 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1316842 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.3380. Min Act: -0.0000

Data Index: 918152 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1250414 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1455203 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1537973 (The Pile)

Max Activating Token Index: 299

Text #5

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2900. Min Act: -0.0000

Data Index: 169927 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1390113 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1003840 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2705. Min Act: -0.0000

Data Index: 545497 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2669. Min Act: -0.0000

Data Index: 669582 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1133686 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2751. Min Act: -0.0000

Data Index: 722131 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2563. Min Act: -0.0000

Data Index: 533833 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2168. Min Act: -0.0000

Data Index: 678353 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2445. Min Act: -0.0000

Data Index: 376794 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1315255 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2503. Min Act: -0.0000

Data Index: 113497 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1330320 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1922925 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1514012 (The Pile)

Max Activating Token Index: 666