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

Dataset: The Pile

Neuron 3432 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.6229. Min Act: -0.0000

Data Index: 1834424 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.5064. Min Act: -0.0000

Data Index: 268335 (The Pile)

Max Activating Token Index: 243

Text #2

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1381531 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1152681 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.3891. Min Act: -0.0000

Data Index: 510501 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.3586. Min Act: -0.0000

Data Index: 1944586 (The Pile)

Max Activating Token Index: 668

Text #6

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.3078. Min Act: -0.0000

Data Index: 1429913 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.3966. Min Act: -0.0000

Data Index: 804203 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1800197 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2899. Min Act: -0.0000

Data Index: 941318 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1626642 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1738784 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1911220 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1646. Min Act: -0.0000

Data Index: 875191 (The Pile)

Max Activating Token Index: 429

Text #14

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1147. Min Act: -0.0000

Data Index: 680799 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1688. Min Act: -0.0000

Data Index: 354517 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1244. Min Act: -0.0000

Data Index: 552351 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1938. Min Act: -0.0000

Data Index: 972890 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1511494 (The Pile)

Max Activating Token Index: 154

Text #19

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1413. Min Act: -0.0000

Data Index: 354237 (The Pile)

Max Activating Token Index: 300