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

Dataset: The Pile

Neuron 2224 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.5930. Min Act: -0.0000

Data Index: 438953 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.3232. Min Act: -0.0000

Data Index: 676852 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.3356. Min Act: -0.0000

Data Index: 1699875 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2848. Min Act: -0.0000

Data Index: 1140595 (The Pile)

Max Activating Token Index: 72

Text #4

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2916. Min Act: -0.0000

Data Index: 720058 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2983. Min Act: -0.0000

Data Index: 702951 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1941. Min Act: -0.0000

Data Index: 1949775 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1054183 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1281. Min Act: -0.0000

Data Index: 997466 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1829386 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2283. Min Act: -0.0000

Data Index: 908609 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1919777 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0519. Min Act: -0.0000

Data Index: 777991 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1722597 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0421. Min Act: -0.0000

Data Index: 221724 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1981. Min Act: -0.0000

Data Index: 1336142 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0649. Min Act: -0.0000

Data Index: 1773514 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1129209 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1423023 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0865. Min Act: -0.0000

Data Index: 654253 (The Pile)

Max Activating Token Index: 902