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

Dataset: The Pile

Neuron 1137 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: 3.1448. Min Range: -3.1448

Max Act: 3.0530. Min Act: -0.0000

Data Index: 134547 (The Pile)

Max Activating Token Index: 640

Text #1

Max Range: 3.1448. Min Range: -3.1448

Max Act: 3.1448. Min Act: -0.0000

Data Index: 515477 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.9079. Min Act: -0.0000

Data Index: 1242466 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 3.1448. Min Range: -3.1448

Max Act: 3.0561. Min Act: -0.0000

Data Index: 1813868 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 3.1448. Min Range: -3.1448

Max Act: 3.0176. Min Act: -0.0000

Data Index: 821057 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.7035. Min Act: -0.0000

Data Index: 210110 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.8330. Min Act: -0.0000

Data Index: 502225 (The Pile)

Max Activating Token Index: 601

Text #7

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.8266. Min Act: -0.0000

Data Index: 834480 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.6817. Min Act: -0.0000

Data Index: 1439501 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.6543. Min Act: -0.0000

Data Index: 218665 (The Pile)

Max Activating Token Index: 640

Text #10

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.6193. Min Act: -0.0000

Data Index: 47345 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.7175. Min Act: -0.0000

Data Index: 797198 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.5566. Min Act: -0.0000

Data Index: 625041 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.3852. Min Act: -0.0000

Data Index: 191236 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.4900. Min Act: -0.0000

Data Index: 319475 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.4743. Min Act: -0.0000

Data Index: 607837 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.5918. Min Act: -0.0000

Data Index: 1309730 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.4478. Min Act: -0.0000

Data Index: 448374 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.6899. Min Act: -0.0000

Data Index: 1495878 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 3.1448. Min Range: -3.1448

Max Act: 2.6658. Min Act: -0.0000

Data Index: 1014852 (The Pile)

Max Activating Token Index: 656