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

Dataset: The Pile

Neuron 2489 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: 0.3020. Min Range: -0.3020

Max Act: 0.2990. Min Act: -0.0000

Data Index: 179464 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.3020. Min Act: -0.0000

Data Index: 28068 (The Pile)

Max Activating Token Index: 384

Text #2

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2625. Min Act: -0.0000

Data Index: 656168 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1836910 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2690. Min Act: -0.0000

Data Index: 998497 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2374. Min Act: -0.0000

Data Index: 757964 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1041002 (The Pile)

Max Activating Token Index: 946

Text #7

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2796. Min Act: -0.0000

Data Index: 954916 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1347378 (The Pile)

Max Activating Token Index: 485

Text #9

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1471541 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2373. Min Act: -0.0000

Data Index: 307663 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2126. Min Act: -0.0000

Data Index: 377853 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1215689 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1881419 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2192. Min Act: -0.0000

Data Index: 894641 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2298. Min Act: -0.0000

Data Index: 792769 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2277. Min Act: -0.0000

Data Index: 804379 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2255. Min Act: -0.0000

Data Index: 935740 (The Pile)

Max Activating Token Index: 956

Text #18

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1683177 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1942034 (The Pile)

Max Activating Token Index: 104