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

Dataset: The Pile

Neuron 1339 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: 3.8099. Min Range: -3.8099

Max Act: 3.8099. Min Act: -0.0000

Data Index: 1820575 (The Pile)

Max Activating Token Index: 928

Text #1

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.7673. Min Act: -0.0000

Data Index: 852759 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.4679. Min Act: -0.0000

Data Index: 1952931 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.3157. Min Act: -0.0000

Data Index: 410347 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.4365. Min Act: -0.0000

Data Index: 1383844 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.2502. Min Act: -0.0000

Data Index: 1403026 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.3345. Min Act: -0.0000

Data Index: 1183082 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.3086. Min Act: -0.0000

Data Index: 1018758 (The Pile)

Max Activating Token Index: 821

Text #8

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.3122. Min Act: -0.0000

Data Index: 713363 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.1254. Min Act: -0.0000

Data Index: 326623 (The Pile)

Max Activating Token Index: 417

Text #10

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.1364. Min Act: -0.0000

Data Index: 1420889 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.4253. Min Act: -0.0000

Data Index: 662208 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 3.8099. Min Range: -3.8099

Max Act: 2.9907. Min Act: -0.0000

Data Index: 1604090 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 3.8099. Min Range: -3.8099

Max Act: 2.9537. Min Act: -0.0000

Data Index: 1094260 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.2114. Min Act: -0.0000

Data Index: 1073006 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.4985. Min Act: -0.0000

Data Index: 1272422 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.0427. Min Act: -0.0000

Data Index: 1868477 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.3305. Min Act: -0.0000

Data Index: 1167652 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.1332. Min Act: -0.0000

Data Index: 116492 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 3.8099. Min Range: -3.8099

Max Act: 3.1359. Min Act: -0.0000

Data Index: 766452 (The Pile)

Max Activating Token Index: 512