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

Dataset: The Pile

Neuron 1134 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: 0.3452. Min Range: -0.3452

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1766844 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1037042 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1652884 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2672. Min Act: -0.0000

Data Index: 975628 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1960489 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2462. Min Act: -0.0000

Data Index: 484271 (The Pile)

Max Activating Token Index: 454

Text #6

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1747980 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1850351 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1109201 (The Pile)

Max Activating Token Index: 89

Text #9

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2375. Min Act: -0.0000

Data Index: 536335 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1728798 (The Pile)

Max Activating Token Index: 723

Text #11

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2313. Min Act: -0.0000

Data Index: 188936 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2313. Min Act: -0.0000

Data Index: 549237 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1432474 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1402111 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.1734. Min Act: -0.0000

Data Index: 672125 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2423. Min Act: -0.0000

Data Index: 374908 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1642311 (The Pile)

Max Activating Token Index: 518

Text #18

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2094. Min Act: -0.0000

Data Index: 702968 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 0.3452. Min Range: -0.3452

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1160509 (The Pile)

Max Activating Token Index: 159