Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 132 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.1126. Min Act: -0.0001

Data Index: 1380385 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1743062 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1360288 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0267. Min Act: 0.0000

Data Index: 320088 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0280. Min Act: 0.0001

Data Index: 1416686 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0344. Min Act: 0.0000

Data Index: 468644 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9785. Min Act: -0.0000

Data Index: 561895 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9547. Min Act: 0.0000

Data Index: 845421 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1863201 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9390. Min Act: -0.0000

Data Index: 827799 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9755. Min Act: 0.0000

Data Index: 141596 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1631656 (The Pile)

Max Activating Token Index: 720

Text #12

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1291279 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1281806 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8696. Min Act: -0.0000

Data Index: 263745 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9474. Min Act: -0.0000

Data Index: 362983 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1247080 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1448576 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8606. Min Act: 0.0000

Data Index: 723427 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1518720 (The Pile)

Max Activating Token Index: 60