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

Dataset: The Pile

Neuron 2594 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: 1.8930. Min Range: -1.8930

Max Act: 1.8930. Min Act: -0.0000

Data Index: 991899 (The Pile)

Max Activating Token Index: 282

Text #1

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.6386. Min Act: -0.0000

Data Index: 1829659 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.5984. Min Act: -0.0000

Data Index: 1398720 (The Pile)

Max Activating Token Index: 954

Text #3

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.4854. Min Act: -0.0000

Data Index: 1266408 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.4879. Min Act: -0.0000

Data Index: 275948 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.5828. Min Act: -0.0000

Data Index: 289532 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.5738. Min Act: -0.0000

Data Index: 1629419 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.3443. Min Act: -0.0000

Data Index: 276390 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1229003 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.1463. Min Act: -0.0000

Data Index: 254624 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.2033. Min Act: -0.0000

Data Index: 555700 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.1746. Min Act: -0.0000

Data Index: 632133 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.1743. Min Act: -0.0000

Data Index: 1545337 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1073481 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.0428. Min Act: -0.0000

Data Index: 263364 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1707699 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.0108. Min Act: -0.0000

Data Index: 1029431 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 1.8930. Min Range: -1.8930

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1591468 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 1.8930. Min Range: -1.8930

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1815886 (The Pile)

Max Activating Token Index: 973

Text #19

Max Range: 1.8930. Min Range: -1.8930

Max Act: 0.9137. Min Act: -0.0000

Data Index: 442932 (The Pile)

Max Activating Token Index: 883