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

Dataset: The Pile

Neuron 1039 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: 3.9114. Min Range: -3.9114

Max Act: 3.9114. Min Act: -0.0000

Data Index: 766917 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.8747. Min Act: -0.0000

Data Index: 1146174 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.4338. Min Act: -0.0000

Data Index: 479431 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7422. Min Act: -0.0000

Data Index: 834068 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.6960. Min Act: -0.0000

Data Index: 170185 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.4951. Min Act: -0.0000

Data Index: 1471561 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.4504. Min Act: -0.0000

Data Index: 1004594 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.4340. Min Act: -0.0000

Data Index: 1290744 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.3947. Min Act: -0.0000

Data Index: 1169472 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.0720. Min Act: -0.0000

Data Index: 740707 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.2295. Min Act: -0.0000

Data Index: 752880 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.2104. Min Act: -0.0000

Data Index: 1777220 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.3779. Min Act: -0.0000

Data Index: 489030 (The Pile)

Max Activating Token Index: 99

Text #13

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.3295. Min Act: -0.0000

Data Index: 29998 (The Pile)

Max Activating Token Index: 56

Text #14

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.3018. Min Act: -0.0000

Data Index: 931053 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.2568. Min Act: -0.0000

Data Index: 1525741 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.2645. Min Act: -0.0000

Data Index: 1133182 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.2402. Min Act: -0.0000

Data Index: 158744 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.2239. Min Act: -0.0000

Data Index: 1826841 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.2300. Min Act: -0.0000

Data Index: 270521 (The Pile)

Max Activating Token Index: 448