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

Dataset: The Pile

Neuron 4942 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: 1.7403. Min Range: -1.7403

Max Act: 1.7403. Min Act: -0.0000

Data Index: 668957 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.6456. Min Act: -0.0000

Data Index: 1632650 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.6208. Min Act: -0.0000

Data Index: 201864 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.5091. Min Act: -0.0000

Data Index: 556952 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.5351. Min Act: -0.0000

Data Index: 813110 (The Pile)

Max Activating Token Index: 124

Text #5

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.6299. Min Act: -0.0000

Data Index: 228961 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.4718. Min Act: -0.0000

Data Index: 456588 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.4949. Min Act: -0.0000

Data Index: 454251 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.2314. Min Act: -0.0000

Data Index: 154738 (The Pile)

Max Activating Token Index: 674

Text #9

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.3695. Min Act: -0.0000

Data Index: 189210 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.1938. Min Act: -0.0000

Data Index: 714888 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.3548. Min Act: -0.0000

Data Index: 376837 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.4491. Min Act: -0.0000

Data Index: 1781461 (The Pile)

Max Activating Token Index: 67

Text #13

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.3406. Min Act: -0.0000

Data Index: 741415 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.2918. Min Act: -0.0000

Data Index: 1539581 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1619044 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.2242. Min Act: -0.0000

Data Index: 735383 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.3045. Min Act: -0.0000

Data Index: 460448 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.2953. Min Act: -0.0000

Data Index: 1272547 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.2365. Min Act: -0.0000

Data Index: 656180 (The Pile)

Max Activating Token Index: 190