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

Dataset: The Pile

Neuron 407 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: 0.3945. Min Range: -0.3945

Max Act: 0.3945. Min Act: -0.0000

Data Index: 74982 (The Pile)

Max Activating Token Index: 106

Text #1

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2489. Min Act: -0.0000

Data Index: 713850 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1287718 (The Pile)

Max Activating Token Index: 542

Text #3

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1877179 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1832607 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1300672 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.1808. Min Act: -0.0000

Data Index: 831052 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1124671 (The Pile)

Max Activating Token Index: 910

Text #8

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1796832 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1105418 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2597. Min Act: -0.0000

Data Index: 980089 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2217. Min Act: -0.0000

Data Index: 219587 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1194972 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.1900. Min Act: -0.0000

Data Index: 515549 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2311. Min Act: -0.0000

Data Index: 579338 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1667426 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1044850 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.1566. Min Act: -0.0000

Data Index: 742829 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1611998 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.1715. Min Act: -0.0000

Data Index: 103843 (The Pile)

Max Activating Token Index: 313