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

Dataset: The Pile

Neuron 2490 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: 1.5206. Min Range: -1.5206

Max Act: 1.5206. Min Act: -0.0000

Data Index: 55243 (The Pile)

Max Activating Token Index: 314

Text #1

Max Range: 1.5206. Min Range: -1.5206

Max Act: 1.2378. Min Act: -0.0000

Data Index: 592461 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 1.5206. Min Range: -1.5206

Max Act: 1.1121. Min Act: -0.0000

Data Index: 1729447 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 1.5206. Min Range: -1.5206

Max Act: 1.1031. Min Act: -0.0000

Data Index: 777868 (The Pile)

Max Activating Token Index: 985

Text #4

Max Range: 1.5206. Min Range: -1.5206

Max Act: 1.0039. Min Act: -0.0000

Data Index: 950702 (The Pile)

Max Activating Token Index: 975

Text #5

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1477931 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1471617 (The Pile)

Max Activating Token Index: 398

Text #7

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.9077. Min Act: -0.0000

Data Index: 368423 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.8980. Min Act: -0.0000

Data Index: 523695 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.9112. Min Act: -0.0000

Data Index: 677225 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1048543 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.9236. Min Act: -0.0000

Data Index: 364502 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1606198 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1055226 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.8612. Min Act: -0.0000

Data Index: 919441 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1813850 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1620644 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1628183 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.8515. Min Act: -0.0000

Data Index: 45349 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 1.5206. Min Range: -1.5206

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1931240 (The Pile)

Max Activating Token Index: 735