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

Dataset: The Pile

Neuron 536 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: 1.0239. Min Range: -1.0239

Max Act: 0.9484. Min Act: -0.0000

Data Index: 1223982 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1614503 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9737. Min Act: -0.0000

Data Index: 703489 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1104117 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1105057 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1146859 (The Pile)

Max Activating Token Index: 492

Text #6

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0157. Min Act: -0.0000

Data Index: 67853 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1727600 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9310. Min Act: -0.0000

Data Index: 949302 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8628. Min Act: -0.0000

Data Index: 61916 (The Pile)

Max Activating Token Index: 920

Text #10

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1844389 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1243382 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9585. Min Act: -0.0000

Data Index: 574995 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1402841 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8626. Min Act: -0.0000

Data Index: 534120 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8797. Min Act: -0.0000

Data Index: 277471 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1235277 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8667. Min Act: -0.0000

Data Index: 545306 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1590075 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8940. Min Act: -0.0000

Data Index: 289168 (The Pile)

Max Activating Token Index: 470