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

Dataset: The Pile

Neuron 3276 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: 0.2628. Min Range: -0.2628

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1892343 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1077676 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2318. Min Act: -0.0000

Data Index: 428182 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1723575 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1511324 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2132. Min Act: -0.0000

Data Index: 676759 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1549518 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2199. Min Act: -0.0000

Data Index: 411074 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1939. Min Act: -0.0000

Data Index: 654075 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1841835 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1539951 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1953. Min Act: -0.0000

Data Index: 681168 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1908. Min Act: -0.0000

Data Index: 193068 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2013. Min Act: -0.0000

Data Index: 777929 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1890. Min Act: -0.0000

Data Index: 663870 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1942. Min Act: -0.0000

Data Index: 193661 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1946695 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2125. Min Act: -0.0000

Data Index: 439234 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1845841 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1915. Min Act: -0.0000

Data Index: 622835 (The Pile)

Max Activating Token Index: 927