Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3644 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.4581. Min Act: -0.0000

Data Index: 501666 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.4661. Min Act: -0.0000

Data Index: 1024051 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1143323 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1881. Min Act: -0.0000

Data Index: 672979 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.0734. Min Act: -0.0000

Data Index: 707144 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1105261 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1002341 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1629169 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1394911 (The Pile)

Max Activating Token Index: 308

Text #9

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.0976. Min Act: -0.0000

Data Index: 575095 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.0908. Min Act: -0.0000

Data Index: 268121 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1527. Min Act: -0.0000

Data Index: 1955030 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1101115 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1223243 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1522897 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1941939 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 1.4661. Min Range: -1.4661

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1820313 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1499630 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1131. Min Act: -0.0000

Data Index: 458785 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1847906 (The Pile)

Max Activating Token Index: 227