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

Dataset: The Pile

Neuron 694 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.8404. Min Act: -0.0000

Data Index: 831765 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.9439. Min Act: -0.0000

Data Index: 1073873 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.2192. Min Act: -0.0000

Data Index: 1933040 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.4057. Min Act: -0.0000

Data Index: 966627 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.0362. Min Act: -0.0000

Data Index: 1399888 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.4156. Min Act: -0.0000

Data Index: 948550 (The Pile)

Max Activating Token Index: 499

Text #6

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.0977. Min Act: -0.0000

Data Index: 381011 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.0303. Min Act: -0.0000

Data Index: 1584292 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.0128. Min Act: -0.0000

Data Index: 584768 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 3.9439. Min Range: -3.9439

Max Act: 2.9532. Min Act: -0.0000

Data Index: 320409 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.2644. Min Act: -0.0000

Data Index: 476762 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 3.9439. Min Range: -3.9439

Max Act: 2.7850. Min Act: -0.0000

Data Index: 946177 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.1871. Min Act: -0.0000

Data Index: 269130 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 3.9439. Min Range: -3.9439

Max Act: 2.9705. Min Act: -0.0000

Data Index: 567354 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 3.9439. Min Range: -3.9439

Max Act: 2.9163. Min Act: -0.0000

Data Index: 718451 (The Pile)

Max Activating Token Index: 121

Text #15

Max Range: 3.9439. Min Range: -3.9439

Max Act: 2.7797. Min Act: -0.0000

Data Index: 1068877 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 3.9439. Min Range: -3.9439

Max Act: 2.8778. Min Act: -0.0000

Data Index: 1456897 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 3.9439. Min Range: -3.9439

Max Act: 2.5839. Min Act: -0.0000

Data Index: 611431 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 3.9439. Min Range: -3.9439

Max Act: 3.0023. Min Act: -0.0000

Data Index: 947206 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 3.9439. Min Range: -3.9439

Max Act: 2.6864. Min Act: -0.0000

Data Index: 637480 (The Pile)

Max Activating Token Index: 473