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

Dataset: The Pile

Neuron 483 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.2691. Min Act: -0.0000

Data Index: 1623036 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1300053 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.2374. Min Act: -0.0000

Data Index: 331972 (The Pile)

Max Activating Token Index: 49

Text #3

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1345556 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9496. Min Act: -0.0000

Data Index: 636210 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9221. Min Act: -0.0000

Data Index: 541359 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0539. Min Act: -0.0000

Data Index: 584370 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9869. Min Act: -0.0000

Data Index: 134265 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 1.3583. Min Range: -1.3583

Max Act: 1.0424. Min Act: -0.0000

Data Index: 807999 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9343. Min Act: -0.0000

Data Index: 248525 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1642367 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9183. Min Act: -0.0000

Data Index: 617461 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1298241 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9288. Min Act: -0.0000

Data Index: 455828 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.8354. Min Act: -0.0000

Data Index: 818174 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1132401 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9267. Min Act: -0.0000

Data Index: 120086 (The Pile)

Max Activating Token Index: 298

Text #17

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1956620 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9882. Min Act: -0.0000

Data Index: 227315 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 1.3583. Min Range: -1.3583

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1689918 (The Pile)

Max Activating Token Index: 441