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

Dataset: The Pile

Neuron 1022 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.5377. Min Act: -0.0000

Data Index: 981636 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.6494. Min Act: -0.0000

Data Index: 699072 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1341034 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3568. Min Act: -0.0000

Data Index: 489064 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1332954 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4086. Min Act: 0.0001

Data Index: 703767 (The Pile)

Max Activating Token Index: 960

Text #6

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3163. Min Act: -0.0000

Data Index: 391284 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1607202 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3814. Min Act: -0.0000

Data Index: 1891028 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1877861 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1867000 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1937456 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1804. Min Act: 0.0000

Data Index: 1695462 (The Pile)

Max Activating Token Index: 207

Text #13

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1051588 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2218. Min Act: -0.0000

Data Index: 473275 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1234767 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1985885 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1038. Min Act: 0.0000

Data Index: 903455 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1783. Min Act: -0.0000

Data Index: 817136 (The Pile)

Max Activating Token Index: 807

Text #19

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1654. Min Act: 0.0000

Data Index: 369897 (The Pile)

Max Activating Token Index: 822