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

Dataset: The Pile

Neuron 4799 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9885. Min Range: -5.9885

Max Act: 5.9885. Min Act: -0.0000

Data Index: 1018284 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 5.9885. Min Range: -5.9885

Max Act: 3.3777. Min Act: -0.0000

Data Index: 1113594 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.8415. Min Act: -0.0000

Data Index: 858282 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 5.9885. Min Range: -5.9885

Max Act: 3.2335. Min Act: -0.0000

Data Index: 947679 (The Pile)

Max Activating Token Index: 968

Text #4

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.9514. Min Act: -0.0000

Data Index: 1663953 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.9748. Min Act: -0.0000

Data Index: 1197022 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.8897. Min Act: -0.0000

Data Index: 979509 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.3283. Min Act: -0.0000

Data Index: 546820 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.6173. Min Act: -0.0000

Data Index: 1380180 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.4258. Min Act: -0.0000

Data Index: 452097 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.3914. Min Act: -0.0000

Data Index: 1240743 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.3996. Min Act: -0.0000

Data Index: 1301354 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.2053. Min Act: -0.0000

Data Index: 503479 (The Pile)

Max Activating Token Index: 326

Text #13

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.4696. Min Act: -0.0000

Data Index: 319794 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.2078. Min Act: -0.0000

Data Index: 514025 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.3469. Min Act: -0.0000

Data Index: 1796614 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.4487. Min Act: -0.0000

Data Index: 390696 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.1322. Min Act: -0.0000

Data Index: 785487 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.3163. Min Act: -0.0000

Data Index: 860413 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 5.9885. Min Range: -5.9885

Max Act: 2.3024. Min Act: -0.0000

Data Index: 1917551 (The Pile)

Max Activating Token Index: 665