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

Dataset: The Pile

Neuron 2540 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4994. Min Act: -0.0000

Data Index: 39884 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.5020. Min Act: -0.0000

Data Index: 672662 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1514553 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4337. Min Act: -0.0000

Data Index: 708101 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4272. Min Act: -0.0000

Data Index: 292231 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4664. Min Act: -0.0000

Data Index: 942151 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4138. Min Act: -0.0000

Data Index: 296135 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1563203 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1478987 (The Pile)

Max Activating Token Index: 344

Text #9

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1330785 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4109. Min Act: -0.0000

Data Index: 498844 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1643030 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3696. Min Act: -0.0000

Data Index: 594193 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3825. Min Act: -0.0000

Data Index: 833147 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3141. Min Act: -0.0000

Data Index: 541976 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1524215 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1517359 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1656445 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1505666 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3685. Min Act: -0.0000

Data Index: 920695 (The Pile)

Max Activating Token Index: 790