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

Dataset: The Pile

Neuron 304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1366721 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.0853. Min Act: -0.0000

Data Index: 212542 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 1.2552. Min Range: -1.2552

Max Act: 1.0106. Min Act: -0.0000

Data Index: 428716 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1589021 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.9276. Min Act: -0.0000

Data Index: 658819 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.8457. Min Act: -0.0000

Data Index: 436958 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1210514 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1048952 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.7906. Min Act: -0.0000

Data Index: 765442 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1965045 (The Pile)

Max Activating Token Index: 304

Text #10

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1157210 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1218622 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.7470. Min Act: -0.0000

Data Index: 1401871 (The Pile)

Max Activating Token Index: 364

Text #13

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1760186 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1739152 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.6230. Min Act: -0.0000

Data Index: 696575 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.6905. Min Act: -0.0000

Data Index: 760468 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.6848. Min Act: -0.0000

Data Index: 953643 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.6745. Min Act: -0.0000

Data Index: 334952 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 1.2552. Min Range: -1.2552

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1304362 (The Pile)

Max Activating Token Index: 770