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

Dataset: The Pile

Neuron 425 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1940. Min Range: -3.1940

Max Act: 3.1940. Min Act: -0.0000

Data Index: 427807 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.5957. Min Act: -0.0000

Data Index: 551486 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.5710. Min Act: -0.0000

Data Index: 974618 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.4141. Min Act: -0.0000

Data Index: 145872 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.4416. Min Act: -0.0000

Data Index: 625757 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1793523 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.4042. Min Act: -0.0000

Data Index: 1522940 (The Pile)

Max Activating Token Index: 810

Text #7

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1462919 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.3575. Min Act: -0.0000

Data Index: 973181 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.3322. Min Act: -0.0000

Data Index: 402966 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.3135. Min Act: -0.0000

Data Index: 1760564 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.3222. Min Act: -0.0000

Data Index: 115174 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.1755. Min Act: -0.0000

Data Index: 572590 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1734895 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.3552. Min Act: -0.0000

Data Index: 297465 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.2420. Min Act: -0.0000

Data Index: 270869 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1476244 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.1621. Min Act: -0.0000

Data Index: 106515 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1448107 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 3.1940. Min Range: -3.1940

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1627850 (The Pile)

Max Activating Token Index: 415