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

Dataset: The Pile

Neuron 3478 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: 5.2241. Min Range: -5.2241

Max Act: 4.7217. Min Act: -0.0000

Data Index: 1992626 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 5.2241. Min Range: -5.2241

Max Act: 5.2241. Min Act: -0.0000

Data Index: 1037709 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 5.2241. Min Range: -5.2241

Max Act: 5.0980. Min Act: -0.0000

Data Index: 1217327 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.3466. Min Act: -0.0000

Data Index: 106957 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.4880. Min Act: -0.0000

Data Index: 1817947 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.3311. Min Act: -0.0000

Data Index: 503338 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.1335. Min Act: -0.0000

Data Index: 1974310 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.4522. Min Act: -0.0000

Data Index: 1965703 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.1087. Min Act: -0.0000

Data Index: 1673188 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 5.2241. Min Range: -5.2241

Max Act: 3.9434. Min Act: -0.0000

Data Index: 1650709 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 5.2241. Min Range: -5.2241

Max Act: 3.8886. Min Act: -0.0000

Data Index: 510103 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.0873. Min Act: -0.0000

Data Index: 1175050 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 5.2241. Min Range: -5.2241

Max Act: 3.9462. Min Act: -0.0000

Data Index: 980838 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.5174. Min Act: -0.0000

Data Index: 1315416 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.1544. Min Act: -0.0000

Data Index: 1068946 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 5.2241. Min Range: -5.2241

Max Act: 3.6835. Min Act: -0.0000

Data Index: 1232132 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.2885. Min Act: -0.0000

Data Index: 991739 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 5.2241. Min Range: -5.2241

Max Act: 3.8056. Min Act: -0.0000

Data Index: 765848 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.1191. Min Act: -0.0000

Data Index: 123743 (The Pile)

Max Activating Token Index: 419

Text #19

Max Range: 5.2241. Min Range: -5.2241

Max Act: 4.0603. Min Act: -0.0000

Data Index: 1430939 (The Pile)

Max Activating Token Index: 291