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

Dataset: The Pile

Neuron 3685 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1203589 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2866. Min Act: -0.0000

Data Index: 900392 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2793. Min Act: -0.0000

Data Index: 739340 (The Pile)

Max Activating Token Index: 32

Text #3

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1755057 (The Pile)

Max Activating Token Index: 616

Text #4

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1804577 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1906771 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2395. Min Act: -0.0000

Data Index: 156938 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1644236 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1306430 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2378. Min Act: -0.0000

Data Index: 936995 (The Pile)

Max Activating Token Index: 480

Text #10

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2422. Min Act: -0.0000

Data Index: 293593 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2298. Min Act: -0.0000

Data Index: 281713 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2308. Min Act: -0.0000

Data Index: 976931 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2313. Min Act: -0.0000

Data Index: 175352 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1946096 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1547444 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2053. Min Act: -0.0000

Data Index: 840310 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1356709 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.1914. Min Act: -0.0000

Data Index: 627718 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1362798 (The Pile)

Max Activating Token Index: 263