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

Dataset: The Pile

Neuron 2247 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: 0.9849. Min Range: -0.9849

Max Act: 0.9849. Min Act: -0.0000

Data Index: 1575487 (The Pile)

Max Activating Token Index: 379

Text #1

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1497783 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8622. Min Act: -0.0000

Data Index: 185665 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8543. Min Act: -0.0000

Data Index: 550793 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1757448 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1228968 (The Pile)

Max Activating Token Index: 728

Text #6

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1195928 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1754961 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8526. Min Act: -0.0000

Data Index: 297740 (The Pile)

Max Activating Token Index: 878

Text #9

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1365246 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7595. Min Act: -0.0000

Data Index: 614191 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6773. Min Act: -0.0000

Data Index: 622125 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7270. Min Act: -0.0000

Data Index: 862320 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7216. Min Act: -0.0000

Data Index: 962177 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1061168 (The Pile)

Max Activating Token Index: 858

Text #15

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1993217 (The Pile)

Max Activating Token Index: 463

Text #16

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1706540 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1657422 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1376254 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6300. Min Act: -0.0000

Data Index: 501803 (The Pile)

Max Activating Token Index: 315