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

Dataset: The Pile

Neuron 1646 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.7483. Min Act: -0.0000

Data Index: 348825 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.5976. Min Act: -0.0000

Data Index: 297061 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1708370 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1626125 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4630. Min Act: -0.0000

Data Index: 858703 (The Pile)

Max Activating Token Index: 537

Text #5

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1245078 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1508716 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4313. Min Act: -0.0000

Data Index: 358429 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4424. Min Act: -0.0000

Data Index: 640696 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4681. Min Act: -0.0000

Data Index: 100052 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4201. Min Act: -0.0000

Data Index: 12937 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3964. Min Act: -0.0000

Data Index: 102 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3931. Min Act: -0.0000

Data Index: 918322 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1482583 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1842067 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1461198 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3207. Min Act: -0.0000

Data Index: 593457 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1696978 (The Pile)

Max Activating Token Index: 908

Text #18

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3270. Min Act: -0.0000

Data Index: 777939 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1921233 (The Pile)

Max Activating Token Index: 743