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

Dataset: The Pile

Neuron 3540 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0663. Min Range: -1.0663

Max Act: 1.0663. Min Act: -0.0000

Data Index: 330514 (The Pile)

Max Activating Token Index: 577

Text #1

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1267188 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.8787. Min Act: -0.0000

Data Index: 124350 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1677352 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1468842 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1581704 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.8535. Min Act: -0.0000

Data Index: 877504 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1037820 (The Pile)

Max Activating Token Index: 420

Text #8

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.8212. Min Act: -0.0000

Data Index: 828341 (The Pile)

Max Activating Token Index: 900

Text #9

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1478879 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1754907 (The Pile)

Max Activating Token Index: 56

Text #11

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1960084 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7834. Min Act: 0.0000

Data Index: 52285 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7818. Min Act: -0.0000

Data Index: 791663 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1265970 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7435. Min Act: -0.0000

Data Index: 192483 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1546719 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7846. Min Act: -0.0000

Data Index: 817420 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1506485 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7864. Min Act: -0.0000

Data Index: 566039 (The Pile)

Max Activating Token Index: 898