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

Dataset: The Pile

Neuron 704 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: 1.1091. Min Range: -1.1091

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1401532 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 1.1091. Min Range: -1.1091

Max Act: 1.1091. Min Act: -0.0000

Data Index: 144796 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1554526 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9591. Min Act: -0.0000

Data Index: 96027 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9226. Min Act: -0.0000

Data Index: 93274 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8928. Min Act: -0.0000

Data Index: 338453 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9122. Min Act: -0.0000

Data Index: 296631 (The Pile)

Max Activating Token Index: 324

Text #7

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1138319 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9616. Min Act: -0.0000

Data Index: 719187 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1041724 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9257. Min Act: -0.0000

Data Index: 53148 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1586984 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8312. Min Act: -0.0000

Data Index: 715874 (The Pile)

Max Activating Token Index: 740

Text #13

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8887. Min Act: -0.0000

Data Index: 65238 (The Pile)

Max Activating Token Index: 882

Text #14

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1413813 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8075. Min Act: -0.0000

Data Index: 137222 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8672. Min Act: -0.0000

Data Index: 51003 (The Pile)

Max Activating Token Index: 850

Text #17

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8389. Min Act: -0.0000

Data Index: 277804 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8641. Min Act: -0.0000

Data Index: 117335 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1821004 (The Pile)

Max Activating Token Index: 378