Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1833 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 5.2494. Min Range: -5.2494

Max Act: 5.2494. Min Act: -0.0000

Data Index: 942336 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 5.2494. Min Range: -5.2494

Max Act: 5.0423. Min Act: -0.0000

Data Index: 1977412 (The Pile)

Max Activating Token Index: 598

Text #2

Max Range: 5.2494. Min Range: -5.2494

Max Act: 5.0938. Min Act: -0.0000

Data Index: 830706 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 5.2494. Min Range: -5.2494

Max Act: 4.7970. Min Act: -0.0000

Data Index: 1213599 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 5.2494. Min Range: -5.2494

Max Act: 4.6175. Min Act: -0.0000

Data Index: 172367 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 5.2494. Min Range: -5.2494

Max Act: 4.4394. Min Act: -0.0000

Data Index: 1791224 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 5.2494. Min Range: -5.2494

Max Act: 4.6069. Min Act: -0.0000

Data Index: 1787955 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 5.2494. Min Range: -5.2494

Max Act: 4.9011. Min Act: -0.0000

Data Index: 1567 (The Pile)

Max Activating Token Index: 796

Text #8

Max Range: 5.2494. Min Range: -5.2494

Max Act: 4.5129. Min Act: -0.0000

Data Index: 943122 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 5.2494. Min Range: -5.2494

Max Act: 4.3356. Min Act: -0.0000

Data Index: 1799376 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 5.2494. Min Range: -5.2494

Max Act: 4.2246. Min Act: -0.0000

Data Index: 911690 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 5.2494. Min Range: -5.2494

Max Act: 4.4430. Min Act: -0.0000

Data Index: 526987 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.9862. Min Act: -0.0000

Data Index: 1877067 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.4714. Min Act: -0.0000

Data Index: 1844861 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.2997. Min Act: -0.0000

Data Index: 1497595 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.0838. Min Act: -0.0000

Data Index: 1828987 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.2246. Min Act: -0.0000

Data Index: 803105 (The Pile)

Max Activating Token Index: 451

Text #17

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.5448. Min Act: -0.0000

Data Index: 1095910 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.4183. Min Act: -0.0000

Data Index: 1465056 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.2579. Min Act: -0.0000

Data Index: 54565 (The Pile)

Max Activating Token Index: 411