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

Dataset: The Pile

Neuron 4697 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: 0.7626. Min Range: -0.7626

Max Act: 0.7626. Min Act: -0.0000

Data Index: 220977 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1768928 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1462085 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6468. Min Act: 0.0000

Data Index: 763012 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1127755 (The Pile)

Max Activating Token Index: 1001

Text #5

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1546925 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1269606 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1123857 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1972245 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1525409 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1935551 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6189. Min Act: -0.0000

Data Index: 613658 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1633330 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1519242 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1280393 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6101. Min Act: -0.0000

Data Index: 124557 (The Pile)

Max Activating Token Index: 682

Text #16

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1204405 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5354. Min Act: -0.0000

Data Index: 422453 (The Pile)

Max Activating Token Index: 436

Text #18

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5253. Min Act: -0.0000

Data Index: 98157 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1957038 (The Pile)

Max Activating Token Index: 320