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

Dataset: The Pile

Neuron 1115 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.3769. Min Act: -0.0000

Data Index: 313077 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1136177 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.2193. Min Act: -0.0000

Data Index: 262727 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1151261 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.1258. Min Act: -0.0000

Data Index: 1424045 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.1247. Min Act: -0.0000

Data Index: 1129908 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.1132. Min Act: -0.0000

Data Index: 553668 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.1789. Min Act: -0.0000

Data Index: 974021 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1131278 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.1446. Min Act: -0.0000

Data Index: 259186 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1239851 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1427368 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0628. Min Act: -0.0000

Data Index: 154039 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1144181 (The Pile)

Max Activating Token Index: 288

Text #14

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0648. Min Act: -0.0000

Data Index: 10744 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.9989. Min Act: -0.0000

Data Index: 716688 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1202895 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0381. Min Act: -0.0000

Data Index: 824607 (The Pile)

Max Activating Token Index: 973

Text #18

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1656750 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0376. Min Act: -0.0000

Data Index: 348825 (The Pile)

Max Activating Token Index: 769