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

Dataset: The Pile

Neuron 4023 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: 0.3537. Min Range: -0.3537

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1616234 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1396085 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3168. Min Act: -0.0000

Data Index: 659190 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1685619 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1875909 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1064677 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1672557 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2795. Min Act: -0.0000

Data Index: 123548 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1044818 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2946. Min Act: -0.0000

Data Index: 495944 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1562118 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2798. Min Act: -0.0000

Data Index: 651028 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1576489 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2519. Min Act: -0.0000

Data Index: 890742 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2748. Min Act: -0.0000

Data Index: 928327 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1516044 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1943935 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1928988 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2662. Min Act: -0.0000

Data Index: 87520 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2681. Min Act: -0.0000

Data Index: 389726 (The Pile)

Max Activating Token Index: 557