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

Dataset: The Pile

Neuron 95 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: 0.9946. Min Range: -0.9946

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1260120 (The Pile)

Max Activating Token Index: 938

Text #1

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1540736 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.9388. Min Act: -0.0000

Data Index: 432158 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8587. Min Act: -0.0000

Data Index: 867096 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8773. Min Act: -0.0000

Data Index: 439548 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1778821 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8399. Min Act: -0.0000

Data Index: 990313 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8570. Min Act: 0.0000

Data Index: 1734435 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1295556 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1902473 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1651243 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7793. Min Act: 0.0000

Data Index: 1750104 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7523. Min Act: -0.0000

Data Index: 958132 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1997990 (The Pile)

Max Activating Token Index: 802

Text #14

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8458. Min Act: -0.0000

Data Index: 309895 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7242. Min Act: -0.0000

Data Index: 770391 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1544668 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1378707 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8461. Min Act: -0.0000

Data Index: 558751 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7576. Min Act: -0.0000

Data Index: 862015 (The Pile)

Max Activating Token Index: 324